c review

Engineering Community

Skill notes

Phase 0 — Parameters

Parse any free text on the invocation line (flamenco only, high severity only, use haiku) and pre-fill what it implies. Then make one AskUserQuestion call for whatever is still unresolved. Never silently default a required parameter. Parameter · Values · Inferring it from the invocation threat_model · REMOTE / LOCAL_UNPRIVILEGED / BOTH · "remote", "network", "attacker" → REMOTE; "local", "unprivileged" → LOCAL_UNPRIVILEGED; otherwise ask

Phase 1 — Resolve paths

Stop if neither resolves, rather than running with an empty path — and say which path you resolved, so a copy other than the installed plugin is visible before eight agents run against it. uv must be on PATH: Detect runs the unit enumerator and Assemble runs assemble_findings.py. If uv is missing, say so and stop — the whole review is

Phase 2 — Run the workflow

Invoking this skill is the opt-in to multi-agent orchestration — call Workflow without asking again. A review of a real codebase also runs past any default workflow size guideline; that guideline is advisory and this is the case it exempts. Do not shrink the fan-out to fit it, and do not substitute hand-spawned Agent calls. One Workflow call. scriptPath takes the absolute path resolved in Phase 1; args

Phase 3 — Return the report

Read <output_dir>/REPORT.md and return it. Say once, plainly, next to the findings: no false-positive review ran. Every severity is the reviewer's own (severity_source: "reviewer"), judgeRan is always false, and nothing rejected anything. Expect some of what you are shown to be wrong or out of scope — say so rather than presenting the list as adjudicated, and do not filter

Rationalizations to Reject

"The run mostly worked, so I'll just present the report." A failed agent is uncovered ground, not a rounding error. Report it next to the findings. "Coverage is 80%, that's basically complete." The missing 20% is a list of exact (unit, question) pairs in ledger-gate.json. Name them. "I'll write the findings myself instead of running the workflow." Hand-orchestrating

Fluxly profile Runtime and permissions are inferred by Fluxly static checks, not author declarations or runtime test results.
Domain
Engineering
Author-declared agents
No explicit declaration found; this is not inferred or tested compatibility
Static check
88 / 100 · heuristic scan, not runtime safety proof
Runtime evidence
Not run; no isolated runtime test evidence is currently recorded
Author / version / license
@trailofbits · no license declared
Token usage
Lean
Setup complexity
Guided setup
External API key
Not required
Operating systems
macOS · Linux · Windows
Runtime requirements
Python
Detected file/system behavior
  • Read-only
  • Write / modify
  • Shell exec
Network behavior
Local-only
Install commands
None (reference only)

Heads up: Tool permissions are not declared; actual access depends on the runtime.

01
Phase 0 — Parameters

Parse any free text on the invocation line (`flamenco only`, `high severity only`, `use haiku`) and pre-fill what it implies. Then make one `AskUserQuestion` call for whatever is still unresolved. Never silently default a required parameter. Parameter · Values · Inferring it from the invocation `threat_model` · `REMOTE` / `LOCAL_UNPRIVILEGED` / `BOTH` · "remote", "network", "attacker" → `REMOTE`; "local", "unprivileged" → `LOCAL_UNPRIVILEGED`; otherwise ask

02
Phase 1 — Resolve paths

Stop if neither resolves, rather than running with an empty path — and say which path you resolved, so a copy other than the installed plugin is visible before eight agents run against it. `uv` must be on PATH: Detect runs the unit enumerator and Assemble runs `assemble_findings.py`. If `uv` is missing, say so and stop — the whole review is

03
Phase 2 — Run the workflow

Invoking this skill is the opt-in to multi-agent orchestration — call `Workflow` without asking again. A review of a real codebase also runs past any default workflow size guideline; that guideline is advisory and this is the case it exempts. Do not shrink the fan-out to fit it, and do not substitute hand-spawned `Agent` calls. One `Workflow` call. `scriptPath` takes the absolute path resolved in Phase 1; `args`

04
Phase 3 — Return the report

`Read <output_dir>/REPORT.md` and return it. Say once, plainly, next to the findings: no false-positive review ran. Every severity is the reviewer's own (`severity_source: "reviewer"`), `judgeRan` is always `false`, and nothing rejected anything. Expect some of what you are shown to be wrong or out of scope — say so rather than presenting the list as adjudicated, and do not filter

Discussion

Powered by GitHub Discussions. Sign in with GitHub to comment, react, or subscribe.