Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add besimple-oss/broccoli --skill besimple-broccoli-blindgit clone --depth 1 https://github.com/besimple-oss/broccoliWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/besimple-oss/broccoli/besimple-broccoli-blind)<a href="https://agentmods.dev/skills/besimple-oss/broccoli/besimple-broccoli-blind"><img src="https://agentmods.dev/badge/skills/besimple-oss/broccoli/besimple-broccoli-blind/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/besimple-oss/broccoli/besimple-broccoli-blind"><img src="https://agentmods.dev/badge/skills/besimple-oss/broccoli/besimple-broccoli-blind.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00058 | $0.02370 |
| Opus 5.5 | $0.00023 | $0.00948 |
| Sonnet 5.5 | $0.00012 | $0.00474 |
| Haiku 4.5 | $0.00006 | $0.00237 |
Grade A, and why
besimple-broccoli-blind scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 229 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Sketch -> Auto-select -> Plan -> Critique -> Implement -> Simplify -> Dedup -> Review (blind wrapper)
This is the automation-safe variant of besimple-broccoli.
- It uses the same planning + implementation flow.
- It automatically chooses recommended clarification options.
- It does not open PRs and does not post Linear comments.
Preconditions
- Confirm repo:
git rev-parse --show-toplevel - Ensure CLIs:
codex,claude - Ensure git commits are possible (
user.name/user.emailconfigured)
Required subskills
plan-sketchplan-writeplan-critique-loopimplement-from-planclaude-simplify-wrapperdedupcode-review-loop
Workflow
-
Prepare subagent logs and heartbeat
LOG_DIR="/tmp/codex-subagent-logs/$(basename "$PWD")" HEARTBEAT_SECONDS=60 SUBAGENT_TIMEOUT_SECONDS=7200 mkdir -p "${LOG_DIR}" SKETCH_LOG="${LOG_DIR}/plan-sketch.log" WRITE_LOG="${LOG_DIR}/plan-write.log" CRITIQUE_LOG="${LOG_DIR}/plan-critique.log" SIMPLIFY_LOG="${LOG_DIR}/simplify.log" DEDUP_LOG="${LOG_DIR}/dedup.log" REVIEW_LOG="${LOG_DIR}/code-review.log" : > "${SKETCH_LOG}" : > "${WRITE_LOG}" : > "${CRITIQUE_LOG}" : > "${SIMPLIFY_LOG}" : > "${DEDUP_LOG}" : > "${REVIEW_LOG}"Resolve installed skill directories (so the wrapper works from any repo):
resolve_skill_dir() { local name="$1" local repo_root="" repo_root="$(git rev-parse --show-toplevel 2>/dev/null || pwd)" local candidates=( "$repo_root/.agents/skills/$name" "$repo_root/.claude/skills/$name" "$HOME/.agents/skills/$name" "$HOME/.codex/skills/$name" "$HOME/.claude/skills/$name" ) for d in "${candidates[@]}"; do if [[ -d "$d" ]]; then echo "$d" return 0 fi done echo "Error: skill '$name' not found in repo-scoped or user-scoped skill dirs." >&2 return 1 } BESIMPLE_BROCCOLI_BLIND_SKILL_DIR="$(resolve_skill_dir besimple-broccoli-blind)" PLAN_SKETCH_SKILL_DIR="$(resolve_skill_dir plan-sketch)" PLAN_WRITE_SKILL_DIR="$(resolve_skill_dir plan-write)" PLAN_CRITIQUE_LOOP_SKILL_DIR="$(resolve_skill_dir plan-critique-loop)" SIMPLIFY_SKILL_DIR="$(resolve_skill_dir claude-simplify-wrapper)" DEDUP_SKILL_DIR="$(resolve_skill_dir dedup)" CODE_REVIEW_LOOP_SKILL_DIR="$(resolve_skill_dir code-review-loop)"
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 1mo ago First seen · 229 lines · 58 tokens per session scan A f4e5cd61ab13
besimple-broccoli-blind is a skill published in the GitHub repository besimple-oss/broccoli (283 stars, last pushed 6mo ago), licensed MIT. It adds 58 tokens to every session and 2,370 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
adversarial-reviewer
Use when you want a genuinely critical review of recent changes — before merging a PR, after a sprint, or when you suspect the review is being too agreeable. Forces perspective shifts through three hostile reviewer personas (Saboteur, New Hire, Security Auditor) that play concurrent, crash, retry and malicious-input…
card-review
Internal skill for onboard's semantic review gate. After the deterministic validation gate (which catches invented symbols / hash drift / secrets), this skill drives a sampled claude -p pass that checks whether the TLDR and role are DIRECTIONALLY ACCURATE given the file's structure and head snippet. The deterministic…
review-ticket
Use as a reviewer agent to review another agent's inreview ticket — never your own. Judge whether each acceptance criterion is genuinely met and proven by a test that exercises that criterion's own behaviour, and whether the change is sound, then record an ADVISORY verdict (per-AC evidence + an overall RECOMMEND…
security-review
Use as a REVIEW LENS when judging another agent's diff for security defects — injection, broken authentication or authorization, secrets in code, unsafe deserialisation, SSRF, path traversal, missing validation, mass assignment, insecure defaults — before recommending approval. Invoke on every review of a ticket that…
concurrency-review
Use as a REVIEW LENS when judging another agent's diff for concurrency and data-integrity defects under failure — concurrent writers, unsynchronised read-modify-write and lost updates, temp-file name collisions, non-atomic file writes, cross-process locking and stale-lock leases, crash/pause/retry schedules…
api-design-reviewer
Use when reviewing a PR that adds or changes API endpoints, auditing an existing API for v2 migration, or establishing REST API standards — HTTP semantics, status codes, RFC 9457 problem-details errors, breaking-change detection, pagination, idempotency and concurrency control. Triggers on "API review", "REST design…