• Kernel drivers/modules (Linux, Windows, macOS).
• Managed languages (Java, C#, Python, Go, Rust).
• Embedded/bare-metal code without libc.

coordinator: write context.md → build_run_plan.py → TaskCreate × M
          → spawn primer (foreground) → spawn M workers (parallel)
          → classify Phase-7 outcomes + write findings-index.txt
          → dedup-judge → fp-judge → SARIF safety net → return REPORT.md

context.md

plan.json

worker-prompts/

findings/

findings-index.d/

findings-index.txt

run-summary.md

dedup-summary.md

fp-summary.md

REPORT.md

REPORT.sarif

${C_REVIEW_PLUGIN_ROOT}=${CLAUDE_PLUGIN_ROOT}

Bash: ls "${CLAUDE_PLUGIN_ROOT}/prompts/clusters/buffer-write-sinks.md"

Bash: find ~/.claude -path '*/plugins/c-review/prompts/clusters/buffer-write-sinks.md' -print -quit

• finding_scope_root

  — the user-requested audit subtree. Workers may only file findings whose vulnerable location is inside this subtree.

• context_roots

  — read-only repo roots/files workers and judges may inspect to verify reachability, callers, wrappers, build flags, mitigations, and threat-model details. Default to

  .

  unless the user explicitly forbids broader context. Reading context outside

  finding_scope_root

  is allowed; filing findings there is not.

• "Background spawns parallelize the workers." They do not —

  Agent

  calls in a single assistant message already run concurrently.

  run_in_background=true

  defeats the Phase 6a primer cache, so every worker pays full cache-creation (

  cache_read_input_tokens=0

  ) and the ~15 K-token primer is wasted M times. This is the single most common defect — multiple recent runs spawned 7-of-8 (or all) workers with

  bg=true

  . Default: omit

  run_in_background

  from worker spawns.
• "I'll re-derive the cluster list / paths / pass prefixes inline instead of running

  build_run_plan.py

  ." The script is the only authority for selection and rendering. Paraphrasing it drops fields that the worker self-check requires, producing

  worker-N abort: spawn prompt malformed

  . Always run the script and

  Read plan.json

  .
• "The run partially succeeded — I'll just write

  REPORT.md

  from what completed." Hiding partial runs behind a successful report is a correctness bug. If any Phase-5 cluster task is not

  completed

  , surface it prominently in

  run-summary.md

  and the final response.
• "Zero findings — skip Phase 8." Always run both judges and Phase 8b: dedup-judge writes a minimal no-op

  dedup-summary.md

  on an empty index, fp-judge writes empty

  REPORT.md

  /

  REPORT.sarif

  , and Phase 8b's SARIF generator emits

  results: []

  for the empty case. SARIF consumers depend on a stable artifact set.
• "

  Bash: ls README*

  is fine for the preflight." Under zsh, an unmatched glob aborts the whole compound command before

  2>/dev/null

  runs. Use

  Glob

  (preferred) or

  find

  (never fails on no-match).

STOP — read this before composing the spawn message.

Workers MUST be spawned foreground (no

run_in_background

field, or

run_in_background=false

). "Parallel" here means one assistant message containing M

Agent

calls — that already runs them concurrently. Background spawns are NOT how you parallelize this skill.

Background spawns defeat Phase 6a's primer cache: every worker pays full cache-creation on its first turn (

cache_read_input_tokens=0

), and the primer's ~15 K tokens are wasted M times over. Two real runs (audit logs available) had exactly this symptom — every worker started with

first_cr=0

.

Before sending the spawn message, audit your draft: every

Agent

call must have no

run_in_background

key. If you wrote

run_in_background=true

, delete it.

Agent

N ∈ [1..M]

1. Read: ${output_dir}/worker-prompts/worker-N.txt

2. Pass the file contents verbatim as the

   Agent

   tool's

   prompt

   argument:

subagent_type

c-review:c-review-worker

model

${worker_model}

description

C review worker N

prompt

worker-N.txt

run_in_background

false

true

worker-N abort: spawn prompt malformed

• Passing

  run_in_background=true

  (the dominant historical defect — see warning above).
• Hand-typing the spawn prompt instead of reading

  worker-N.txt

  .
• Inserting Task-related instructions ("first call TaskList", "Assigned task id: <N>"). Workers have no Task tools.
• Editing the rendered prompt before passing it (trimming "redundant" fields, collapsing pass lists).

findings-index.txt

dedup-summary.md

fp-summary.md

REPORT.md

REPORT.sarif

agents/c-review-{dedup,fp}-judge.md

prompts/internal/judges/

• Agent(subagent_type="c-review:c-review-dedup-judge", description="Dedup judge", prompt=f"output_dir: {output_dir}")

• Agent(subagent_type="c-review:c-review-fp-judge", description="FP + severity judge", prompt=f"output_dir: {output_dir}\nsarif_generator_path: {sarif_generator_path}")

  — resolve

  sarif_generator_path

  to

  ${C_REVIEW_PLUGIN_ROOT}/scripts/generate_sarif.py

  .

• … complete:

  → success.

• … abort:

  → non-retryable. Surface the abort line plus

  ls -l ${output_dir}/findings-index.txt

  ; stop.
• No

  complete:

  (help message / error / question) → retryable once.

  SendMessage(to=<agentId>, …)

  rather than a fresh spawn (the agent already paid the protocol-parse cost). Include the explicit finding paths from

  findings-index.txt

  . If the second try still fails, surface the transcript and continue to Phase 8b.

agents/c-review-worker.md

1. Worker — base fields (

   id

   ,

   bug_class

   ,

   title

   ,

   location

   ,

   function

   ,

   confidence

   ,

   worker

   ) + seven body sections.
2. Dedup-judge — adds

   merged_into

   on duplicates, or

   also_known_as

   +

   locations

   on primaries that absorbed.
3. FP+Severity judge — adds

   fp_verdict

   +

   fp_rationale

   on every primary; on survivors (

   TRUE_POSITIVE

   /

   LIKELY_TP

   ) also adds

   severity

   ,

   attack_vector

   ,

   exploitability

   ,

   severity_rationale

   .

• Every Phase-5 cluster task is

  completed

  (verify via

  TaskList

  ).

• ${output_dir}/run-summary.md

  exists and records resolved scope/context, compile-commands probe result, worker claims vs index count, task status, and judge/SARIF status.
• Every primary finding (no

  merged_into

  ) has

  fp_verdict

  +

  fp_rationale

  ; every survivor (

  TRUE_POSITIVE

  /

  LIKELY_TP

  ) also has

  severity

  ,

  attack_vector

  ,

  exploitability

  ,

  severity_rationale

  .

• REPORT.md

  exists, severity-filtered per

  severity_filter

  .

• REPORT.sarif

  exists (Phase 8b safety net guarantees this).