age

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese

/age

/age

Review a diff or scoped path before merging, after
/press
, or whenever the user wants evidence-backed observations rather than an approval verdict. Do not apply fixes here —
/cure
owns application.
在合并前、执行
/press
后,或用户需要基于证据的观察而非批准结论时,审查代码差异或限定范围的路径。请勿在此处应用修复——修复操作由
/cure
负责。

Inputs

输入参数

text
/age [<ref-or-range>] [--scope <path>] [--comprehensive] [--full] [--safe] [--open-pr] [--auto] [--html]
/age <slug> [--full] [--safe] [--open-pr] [--auto] [--html]
--full
un-collapses the
## Low
section when 10 or more low-severity findings exist (the default report collapses them to a one-line summary).
--safe
re-introduces cure selection.
--open-pr
propagates through
/cure
to terminal
/plate
; a new PR follows
/plate
's explicit-choice and review-shape policy.
When called with a
<slug>
, resolve
.cheese/press/<slug>.md
(if present) for press context and review the current working diff. When called with a
<ref-or-range>
, review that range. Default to the current working diff when neither is supplied. If the base branch is unclear, ask or use the repository's documented default.
--auto
is the propagated autonomous-mode flag from
/cook --auto
. It changes the handoff (see
## Handoff
and
## Auto mode
for the cap rule and full chain).
--hard
propagates through
/cure
to
/plate
. Age never fires the gate;
/plate
gives
/hard-cheese
the final verified artifact state before publication.
--html
emits a static HTML copy alongside
.cheese/age/<slug>.md
: write the markdown first, then
python3 src/age/age-html-report.py --report .cheese/age/<slug>.md --slug <slug>
(bundle fallback:
age.pyz html-report
with the same flags), and print the returned path. It groups findings by severity into the shared HTML shell (
shared/scripts/html_report.render_document
) — offline, no CDN, no JS.
Portability reference:
../cheese/references/harness-portability.md
covers helper resolution, sub-agent dispatch, GitHub operations, and handoff transitions; prefer the bundled or repo-local helper first, treat
${CLAUDE_SKILL_DIR}
as optional host-provided fallback. The handoff blocks below are the portable contract; slash commands are host renderings, not the control model.
text
/age [<ref-or-range>] [--scope <path>] [--comprehensive] [--full] [--safe] [--open-pr] [--auto] [--html]
/age <slug> [--full] [--safe] [--open-pr] [--auto] [--html]
--full
:当存在10个及以上低严重程度发现时,展开
## Low
章节(默认报告将其折叠为单行摘要)。
--safe
:重新启用修复选项。
--open-pr
会通过
/cure
传递至最终的
/plate
;新PR遵循
/plate
的明确选择和审查形态策略。
当传入
<slug>
时,解析
.cheese/press/<slug>.md
(如果存在)以获取press上下文,并审查当前工作差异。当传入
<ref-or-range>
时,审查该范围。若两者均未提供,默认审查当前工作差异。若基准分支不明确,询问用户或使用仓库文档中指定的默认分支。
--auto
是从
/cook --auto
传递的自动模式标志。它会改变交接流程(详见
## Handoff
## Auto mode
中的限制规则及完整流程链)。
--hard
通过
/cure
传递至
/plate
。Age从不触发闸门;
/plate
会在发布前将最终验证的工件状态传递给
/hard-cheese
--html
会在
.cheese/age/<slug>.md
旁生成静态HTML副本:先写入markdown,再执行
python3 src/age/age-html-report.py --report .cheese/age/<slug>.md --slug <slug>
(备用捆绑包:
age.pyz html-report
并使用相同参数),然后打印返回的路径。它会按严重程度将发现分组到共享的HTML框架中(
shared/scripts/html_report.render_document
)——离线可用,无需CDN,无JS。
可移植性参考:
../cheese/references/harness-portability.md
涵盖了助手解析、子代理调度、GitHub操作和交接转换;优先使用捆绑包或仓库本地助手,将
${CLAUDE_SKILL_DIR}
视为可选的宿主提供的备用方案。以下交接块是可移植契约;斜杠命令是宿主呈现形式,而非控制模型。

Review dimensions

审查维度

Dimensions answer what kind of problem. Severity (
blocker / high / medium / low
) is per-finding, computed from base + location + compounding modifiers (see
references/dimensions.md
§ Severity computation).
DimensionBase range
correctnesslow → blocker
securitylow → blocker
encapsulationlow → blocker
speclow → blocker
complexitylow → high
desloplow → high
assertionslow → blocker
nihlow → high
efficiencylow → blocker
telemetrylow → blocker
Per-dimension base-severity tables, location-sensitivity, fix-cost-now / fix-cost-later, and recommendation shapes live in
references/dimensions.md
— read it before computing any finding's severity. This reduced workflow intentionally omits the git-history/precedent dimension.
维度用于说明问题类型。严重程度(
blocker / high / medium / low
)针对每个发现,由基础值+位置+复合修正项计算得出(详见
references/dimensions.md
中的“严重程度计算”章节)。
维度基础范围
correctnesslow → blocker
securitylow → blocker
encapsulationlow → blocker
speclow → blocker
complexitylow → high
desloplow → high
assertionslow → blocker
nihlow → high
efficiencylow → blocker
telemetrylow → blocker
各维度的基础严重程度表、位置敏感性、即时修复成本/后续修复成本以及建议形态均收录于
references/dimensions.md
——在计算任何发现的严重程度前,请先阅读该文档。此简化工作流程有意省略了git历史/先例维度。

Flow

流程

  1. Identify the diff, scope, and relevant spec or issue. Mode check: compute the review range's
    review_surface
    score and risk flags, then call
    age_route.route(score=..., risk_flags=..., entry="age")
    (
    src/fanout/age_route.py
    ).
    n=1
    — steps 2–4 below, unchanged. Any
    n>1
    — read
    references/fan-out.md
    first; its
    lenses
    list, not a fixed label, sets worker count. Fan-out also requires
    /age
    not itself be a sub-agent — stay single-parent when it is. Thread the router's
    effort
    into the reviewer dispatch.
  2. Gather evidence: diff, touched files, tests, callers/imports. If a press report exists for this slug, read it via
    python3 shared/scripts/read_handoff_slug.py --phase press --slug <slug>
    (bundle fallback:
    common.pyz read_handoff_slug --phase press --slug <slug>
    ) and summarise unresolved items in a
    ## Press findings
    sub-section —
    /cure
    only reads
    .cheese/age/<slug>.md
    .
    No press report but a cook handoff exists: record
    press: skipped
    (see
    ## Output
    ) and print the warning at handoff. No cook artifact either: skip the marker and continue.
    If
    .cheese/glossary/<slug>.md
    exists, read it so naming drift can be flagged as a deslop finding.
  3. Review every dimension; dimensions with no findings simply omit themselves. Report every defect, however minor — never self-filter on perceived significance; filtering happens downstream in the verifier pass (
    n>1
    ) or in severity computation (single-parent). Do not raise a finding for a gate failure identical to the diff's recorded
    baseline:
    block — see
    ../cook/references/quality-gates.md
    ; flag only new or changed failures.
  4. Compute severity per finding (base + location bump + compounding bump, capped at
    blocker
    ). Group findings by severity (
    ## Blocker → ## High → ## Medium → ## Low
    ); within a severity group, order by file.
  5. Write the report (see
    ## Output
    ), then
    python3 shared/scripts/write_handoff_artifact.py --phase age --slug <slug> --status ok --next cure --artifact "" --orientation "<one-line orientation>" --durable-flags "<none | one line per flag>" --body-file "$report_file"
    (bundle fallback:
    ${CLAUDE_SKILL_DIR}/scripts/common.pyz write_handoff_artifact
    with the same flags). Print the path.
  6. Hand off (see
    ## Handoff
    below).
  1. 识别差异、范围及相关规范或问题。模式检查:计算审查范围的
    review_surface
    分数和风险标志,然后调用
    age_route.route(score=..., risk_flags=..., entry="age")
    src/fanout/age_route.py
    )。若
    n=1
    ,则执行以下步骤2-4,流程不变。若
    n>1
    ,请先阅读
    references/fan-out.md
    ;其中的
    lenses
    列表(而非固定标签)决定了工作者数量。扇出还要求
    /age
    本身不是子代理——当它是子代理时,保持单父结构。将路由器的
    effort
    参数传入审查器调度。
  2. 收集证据:差异、被修改文件、测试、调用者/导入项。如果该slug存在press报告,通过
    python3 shared/scripts/read_handoff_slug.py --phase press --slug <slug>
    (备用捆绑包:
    common.pyz read_handoff_slug --phase press --slug <slug>
    )读取并在
    ## Press findings
    子章节中总结未解决的问题——
    /cure
    仅读取
    .cheese/age/<slug>.md
    若不存在press报告但存在cook交接记录:记录
    press: skipped
    (详见
    ## Output
    )并在交接时打印警告。若也不存在cook工件,则跳过标记并继续。
    .cheese/glossary/<slug>.md
    存在,读取该文件以便将命名偏差标记为deslop发现。
  3. 审查所有维度;无发现的维度直接省略。报告所有缺陷,无论多细微——切勿自行过滤认为不重要的问题;过滤操作会在下游的验证阶段(
    n>1
    )或严重程度计算(单父结构)中进行。对于与diff中记录的
    baseline:
    块完全相同的闸门失败,请勿提出发现——详见
    ../cook/references/quality-gates.md
    ;仅标记新出现或已更改的失败。
  4. 计算每个发现的严重程度(基础值+位置提升+复合提升,上限为
    blocker
    )。按严重程度分组(
    ## Blocker → ## High → ## Medium → ## Low
    );在同一严重程度组内,按文件排序。
  5. 撰写报告(详见
    ## Output
    ),然后执行
    python3 shared/scripts/write_handoff_artifact.py --phase age --slug <slug> --status ok --next cure --artifact "" --orientation "<单行描述>" --durable-flags "<none | 每行一个标志>" --body-file "$report_file"
    (备用捆绑包:
    ${CLAUDE_SKILL_DIR}/scripts/common.pyz write_handoff_artifact
    并使用相同参数)。打印报告路径。
  6. 交接(详见下方
    ## Handoff
    )。

Preferred tools and fallbacks

首选工具及备选方案

Call source-code backends directly according to the shared
code-intelligence-routing.md
contract. For caller graphs, use the selected semantic backend's caller query plus
tilth_deps
when available.
NeedPreferFallback
Diff inspection
delta
git diff --unified=3
Caller/dependency impact + curated review contextsemantic caller search +
tilth_deps
manual scoping; note the precision loss
Architecture / hotspot framing for large diffschanged-file map + caller/dependency evidenceskip and note in confidence
Design rationale for encapsulation/spec dimensions (optional)
mcp__hallouminate__list_corpora
/
mcp__hallouminate__ground
on
repo:<repo>:wiki
, grounding design intent before grading, rendering consulted pages in
## Wiki context
skip; omit
## Wiki context
; proceed with diff + code evidence only; cap at
speculating
when rationale is the primary evidence
GitHub/PR context
gh
local git commands or user-provided PR data
Merge/conflict awarenessmergirafmanual conflict checks
Optional MCPs: hallouminate and milknado follow the detect-and-degrade contract in
../cheese/references/optional-plugins.md
— state absence once, fall back, reduce confidence only if evidence quality suffers, never block.
根据共享的
code-intelligence-routing.md
契约直接调用源代码后端。对于调用图,优先使用所选语义后端的调用查询+
tilth_deps
(如果可用)。
需求首选方案备选方案
差异检查
delta
git diff --unified=3
调用者/依赖影响 + 精心整理的审查上下文语义调用搜索 +
tilth_deps
手动范围界定;记录精度损失
大型差异的架构/热点框架修改文件映射 + 调用者/依赖证据跳过并记录置信度
封装/规范维度的设计原理(可选)
mcp__hallouminate__list_corpora
/
mcp__hallouminate__ground
基于
repo:<repo>:wiki
,在评分前明确设计意图,在
## Wiki context
中呈现查阅的页面
跳过;省略
## Wiki context
;仅基于差异+代码证据继续;若原理是主要证据,则置信度上限为
speculating
GitHub/PR上下文
gh
本地git命令或用户提供的PR数据
合并/冲突感知mergiraf手动冲突检查
可选MCP:hallouminate和milknado遵循
../cheese/references/optional-plugins.md
中的检测降级契约——仅声明一次缺失,然后降级;仅当证据质量受影响时降低置信度,绝不阻塞流程。

Sub-agent fan-out

子代理扇出

/age
sizes its own fan-out via the age router (
src/fanout/age_route.py
), not a size-only threshold, and resolves every dispatched worker through
../cheese/references/agent-resolution.md
(read-only, fresh-context; exact specialist, then compatible specialist, then a prompt-constrained general agent with
degraded: true
). Mechanics:
references/fan-out.md
,
references/packet.md
,
references/sub-agent-gate.md
.
/age
通过age路由器(
src/fanout/age_route.py
)而非仅基于大小的阈值来确定自身扇出规模,并通过
../cheese/references/agent-resolution.md
解析所有调度的工作者(只读、新鲜上下文;优先选择精准专家,然后是兼容专家,最后是带有
degraded: true
的提示约束通用代理)。机制详见:
references/fan-out.md
references/packet.md
references/sub-agent-gate.md

Output

输出

Cross-cutting house style and citation form:
../cheese/references/formatting.md
. This section owns the findings-report shape; formatting.md owns the voice rules and the footnote primitive.
Write to
.cheese/age/<slug>.md
with a minimum handoff slug at the top —
status
,
next
,
artifact
,
durable_flags
,
baseline
, one-line orientation.
press: skipped
is the first body line after the blank separator when a cook artifact exists but no press report does; omit it otherwise.
Body, in order:
# Age Report — <slug>
;
## Orientation
(1-2 sentences);
## Press findings
(omit unless a press report exists);
## Wiki context
(omit unless hallouminate grounding hit); severity sections (
**[dim:sev]** path:line — claim
, then
location: <tier> · fix-cost-now: <tier> · fix-cost-later: <tier> · confidence: <tier>
, then
recommendation: <action>
);
## Confidence
;
## Next step
. See
references/report-example.md
for the full skeleton plus a worked instantiation.
Empty severity sections are omitted entirely. When ten or more
low
findings exist, collapse the
## Low
section to a single line:
markdown
undefined
跨领域格式规范及引用形式:
../cheese/references/formatting.md
。本节定义了发现报告的结构;formatting.md定义了表述规则和脚注格式。
写入
.cheese/age/<slug>.md
,顶部包含最少交接信息——
status
next
artifact
durable_flags
baseline
、单行描述。当存在cook工件但无press报告时,在空白分隔符后的第一行写入
press: skipped
;否则省略。
正文顺序:
# Age Report — <slug>
## Orientation
(1-2句话);
## Press findings
(仅当存在press报告时保留);
## Wiki context
(仅当hallouminate找到相关内容时保留);严重程度章节(
**[dim:sev]** path:line — 问题描述
,然后是
location: <层级> · fix-cost-now: <层级> · fix-cost-later: <层级> · confidence: <层级>
,最后是
recommendation: <操作建议>
);
## Confidence
## Next step
。完整框架及示例详见
references/report-example.md
空的严重程度章节将完全省略。当存在10个及以上
low
发现时,将
## Low
章节折叠为单行:
markdown
undefined

Low

Low

N low-severity findings suppressed. Re-run with
--full
(or
/age --full
) to see them.

Per-finding `confidence:` uses the voice-kernel scale (`references/voice.md` § Reasoning posture): `certain` — verified by direct evidence (diff/code read, command output); `speculating` — inferred from indirect signal. A `don't know` grading never ships as a finding row — gather the missing evidence or drop the claim. Suppressed lows feed the cure-selection table only when `--full` is passed.

`status: ok` when the review completed; `status: halt: <reason>` when evidence was unreachable. `next: cure` when any finding meets the **medium+ floor**; `next: done` otherwise. `durable_flags:` mirrors cook's gate: default `none`.

Then print `Age report: .cheese/age/<slug>.md`. When `press: skipped` is set, also print: `Warning: no /press report for <slug> — hardening was skipped. Run /press <slug> first, or continue with /cure.` When `--html` is passed, also print the HTML path returned by `html-report` (render command under `--html` in `## Inputs`).
已隐藏N个低严重程度发现。使用
--full
(或
/age --full
)重新运行以查看详情。

每个发现的`confidence:`使用核心表述尺度(`references/voice.md`中的“推理姿态”章节):`certain`——由直接证据验证(差异/代码阅读、命令输出);`speculating`——由间接信号推断。`don't know`评级绝不会作为发现行输出——要么收集缺失证据,要么放弃该结论。仅当传递`--full`时,被隐藏的低严重程度发现才会纳入修复选择表。

当审查完成时,`status: ok`;当证据无法获取时,`status: halt: <原因>`。当任何发现达到**medium及以上**标准时,`next: cure`;否则`next: done`。`durable_flags:`与cook的闸门一致:默认值为`none`。

然后打印`Age report: .cheese/age/<slug>.md`。当设置了`press: skipped`时,还需打印:`Warning: no /press report for <slug> — hardening was skipped. Run /press <slug> first, or continue with /cure.`当传递`--html`时,还需打印`html-report`返回的HTML路径(`## Inputs`中`--html`下的渲染命令)。

Handoff

交接

Pipeline: culture → mold → cook → press → [age] → cure → plate
Compute the recommended set. Composite
all-medium, cheap
: the medium floor (blocker+high+medium) unioned with every
Low
at
fix-cost-now: contained
.
Decide act vs ask:
  • Empty set — write
    next: done
    , print the report path, stop.
  • Reason to ask — a set member has
    fix-cost-now: sprawling
    or
    fix-cost-later: structural
    , findings conflict, or
    --safe
    was passed: read
    references/handoff-detail.md
    and render the gate per
    ../cheese/references/handoff-gate.md
    , pre-selecting the composite and flagging heavy rows.
  • Otherwise — act: announce the selection and dispatch
    /cure
    per
    references/handoff-detail.md
    § Dispatch. No gate.
--auto
substitutes a severity-floor selection (
## Auto mode
below);
references/handoff-detail.md
also covers the no-chain override under
/cook
's fan pathway.
流水线:culture → mold → cook → press → [age] → cure → plate
计算推荐集:合并
all-medium, cheap
:即medium及以上严重程度(blocker+high+medium)加上所有
fix-cost-now: contained
Low
发现。
决定执行还是询问
  • 空集——写入
    next: done
    ,打印报告路径,停止流程。
  • 需要询问的情况——集合中存在
    fix-cost-now: sprawling
    fix-cost-later: structural
    的发现、发现存在冲突,或传递了
    --safe
    :阅读
    references/handoff-detail.md
    并根据
    ../cheese/references/handoff-gate.md
    呈现闸门,预先选择推荐集并标记复杂项。
  • 其他情况——执行:宣布选择结果并根据
    references/handoff-detail.md
    中的“调度”章节调度
    /cure
    。无需闸门。
--auto
会替换为基于严重程度阈值的选择(详见下方
## Auto mode
);
references/handoff-detail.md
还涵盖了
/cook
扇出路径下的无链覆盖规则。

Auto mode

自动模式

When invoked with
--auto
:
  • Skip the handoff gate.
  • If two cure passes have already completed (cap reached), stop and surface the final report — do not invoke
    /cure
    again even if findings remain.
  • Otherwise, if any finding meets the medium+ floor — invoke
    /cure <slug> --auto --stake medium+
    (forward
    --open-pr
    when it is in scope) and increment the cure-pass count when it returns.
  • If no finding meets the medium+ floor, stop the chain with a one-line "auto chain clean" note and the report path.
当使用
--auto
调用时:
  • 跳过交接闸门。
  • 若已完成两次cure流程(达到上限),停止并展示最终报告——即使仍有发现,也不再调用
    /cure
  • 否则,若任何发现达到medium及以上标准——调用
    /cure <slug> --auto --stake medium+
    (若适用则传递
    --open-pr
    ),并在返回时增加cure流程计数。
  • 若没有发现达到medium及以上标准,以一行“auto chain clean”提示和报告路径停止流程链。

Within cook's own fan pathway

在cook自身的扇出路径中

/cook
's fan pathway spawns age as a fresh-context sub-agent and owns the chain itself. Read
references/handoff-detail.md
§ Within cook's own fan pathway for the no-chain isolation directive before writing the report.
/cook
的扇出路径会生成一个作为子代理的fresh-context age,并自行管理流程链。在撰写报告前,请阅读
references/handoff-detail.md
中的“在cook自身的扇出路径中”章节,遵循无链隔离指令。

Rules

规则

  • Review is not a verdict; explain where to look and why.
  • Do not edit production files;
    /cure
    owns application.
  • Do not raise a finding for a gate failure identical to the diff's recorded
    baseline:
    block; flag only new/changed failures per
    ../cook/references/quality-gates.md
    .
  • Default to acting: auto-select the recommended set, dispatch
    /cure
    without a gate. Ask first only on a genuine reason or
    --safe
    . An empty recommended set is a clean stop, not a question.
  • Do not invent evidence; cite files, diffs, commands, or unavailable-source notes.
  • Agree when the diff is fine — an empty dimension is a valid outcome, not a gap to fill.
  • Keep confidence qualitative (
    certain | speculating | don't know
    ) at both the report and per-finding level; never a numeric score.
  • Findings carry location + recommendation, not JSON sidecars or tag-anchored fix payloads —
    /cure
    reads the markdown directly.
  • Apply
    references/voice.md
    (output discipline, reasoning posture, confidence vocabulary).
  • 审查并非裁决;需说明问题位置及原因。
  • 请勿编辑生产文件;
    /cure
    负责应用修复。
  • 对于与diff中记录的
    baseline:
    块完全相同的闸门失败,请勿提出发现;仅根据
    ../cook/references/quality-gates.md
    标记新出现或已更改的失败。
  • 默认执行:自动选择推荐集,无需闸门直接调度
    /cure
    。仅在确实需要或传递
    --safe
    时才先询问。空推荐集表示流程干净结束,而非需要询问。
  • 请勿编造证据;需引用文件、差异、命令或无法获取源的说明。
  • 若diff无问题则确认——空维度是有效结果,而非需要填补的空白。
  • 在报告和每个发现层面保持定性的置信度(
    certain | speculating | don't know
    );绝不使用数字评分。
  • 发现需包含位置+建议,而非JSON附加数据或带标签的修复负载——
    /cure
    直接读取markdown。
  • 遵循
    references/voice.md
    (输出规范、推理姿态、置信度词汇)。

References

参考文档

  • references/dimensions.md
    — before grading any finding: rubrics, location sensitivity, fix-cost tables, recommendation shapes.
  • references/fan-out.md
    — before any
    n>1
    dispatch: router mechanics, lens partitions, six-seam sequence, verifier pass.
  • references/packet.md
    — when assembling the Seam-2 shared context packet for a fan-out run.
  • references/sub-agent-gate.md
    — before any sub-agent dispatch: digest contract, harness-agnostic selection, what the parent never delegates.
  • references/handoff-detail.md
    — before the selection gate or a
    /cure
    dispatch: gate menu, dispatch payload, cook-fan-pathway no-chain override.
  • references/report-example.md
    — alongside
    ## Output
    : worked rendering plus the full placeholder skeleton.
  • references/voice.md
    — when writing the report: output discipline, reasoning posture, confidence vocabulary.
  • references/deslop-rust.md
    ,
    references/deslop-typescript.md
    ,
    references/deslop-python.md
    ,
    references/deslop-shell.md
    ,
    references/deslop-go.md
    — when grading
    deslop
    in that language: pattern catalogs with lint-rule mappings.
  • references/dimensions.md
    ——在对任何发现评分前阅读:评分标准、位置敏感性、修复成本表、建议形态。
  • references/fan-out.md
    ——在任何
    n>1
    调度前阅读:路由器机制、透镜分区、六阶段流程、验证阶段。
  • references/packet.md
    ——当为扇出运行组装Seam-2共享上下文包时阅读。
  • references/sub-agent-gate.md
    ——在任何子代理调度前阅读:摘要契约、与 harness 无关的选择、父代理绝不委托的内容。
  • references/handoff-detail.md
    ——在选择闸门或调度
    /cure
    前阅读:闸门菜单、调度负载、cook扇出路径的无链覆盖规则。
  • references/report-example.md
    ——结合
    ## Output
    阅读:示例渲染及完整占位符框架。
  • references/voice.md
    ——撰写报告时阅读:输出规范、推理姿态、置信度词汇。
  • references/deslop-rust.md
    references/deslop-typescript.md
    references/deslop-python.md
    references/deslop-shell.md
    references/deslop-go.md
    ——在对对应语言的
    deslop
    评分时阅读:带有lint规则映射的模式目录。

Agent resolution

代理解析

Resolve every dimension worker and fresh-context review through
../cheese/references/agent-resolution.md
.
WorkPreferred typesPermissions/isolationMinimum powerEffortFallback
Review a diff or one dimensionreviewerread-only, fresh-contextpowerfulhighcompatible reviewer, then general
The canonical age report/handoff carries the shared
agent_resolution
block.
通过
../cheese/references/agent-resolution.md
解析所有维度工作者和fresh-context审查器。
工作内容首选类型权限/隔离最低能力工作量备选方案
审查差异或单个维度reviewer只读、新鲜上下文强能力兼容reviewer,然后是通用代理
标准的age报告/交接包含共享的
agent_resolution
块。