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.
git clone --depth 1 https://github.com/yeisonrestrepo/code-conductorWrote 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/commands/yeisonrestrepo/code-conductor/cc-review)<a href="https://agentmods.dev/commands/yeisonrestrepo/code-conductor/cc-review"><img src="https://agentmods.dev/badge/commands/yeisonrestrepo/code-conductor/cc-review/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/commands/yeisonrestrepo/code-conductor/cc-review"><img src="https://agentmods.dev/badge/commands/yeisonrestrepo/code-conductor/cc-review.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 | $0.00011 | $0.00653 |
| Opus 5.5 | $0.00004 | $0.00261 |
| Sonnet 5.5 | $0.00002 | $0.00131 |
| Haiku 4.5 | $0.00001 | $0.00065 |
Grade A, and why
cc-review 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 — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Phase entry - Handoff enforcement
Before doing anything else, perform this blocking check:
-
Count the number of turns in the current conversation history.
-
If turn count exceeds 5, halt immediately and output:
"Phase boundary detected. Please execute /compact to clear history before proceeding."
Do not start any review tasks. Enter standby. Wait for the user to confirm
/compacthas been run before continuing. -
If turn count ≤ 5 AND
.claude/memory/session-snapshot.mdexists, proceed to the Destructive Read Invariant below. -
If turn count ≤ 5 AND
.claude/memory/session-snapshot.mdis absent, skip the Destructive Read Invariant and proceed directly - no snapshot context available (read-if-present fallback).
Phase entry - Destructive Read Invariant
Applies only when snapshot exists (step 3 above).
- Read
.claude/memory/session-snapshot.mdinto context. - Delete the file immediately.
- Use the snapshot contents as the starting context for this phase.
If the file cannot be deleted after reading, report the error and halt.
Phase 0 — Skill activation
Before doing anything else, invoke both skills in order:
Skill({ skill: "subagent-driven-development", args: "$ARGUMENTS" })
Skill({ skill: "critical-review" })
subagent-driven-development spawns one Explore sub-agent per review layer (Critical / Important / Suggestions) — each returns findings, the main context aggregates only. critical-review then runs Phases 2–4: Adversarial Review (RESILIENCE / EFFICIENCY / FRICTION checks), Self-Correction Loop for any weakness found, and the mandatory [VALIDATION] section at the end.
Determine what to review:
- No argument →
git diff HEAD - File path → review that file
- Directory → review all changed files in that directory
Review in three layers:
🔴 Critical — Blocks merge
Issues that will cause bugs, security vulnerabilities, data loss, or breaking changes:
- Logic errors or incorrect algorithm
- SQL injection, XSS, hardcoded secrets, missing auth checks
- Mutations that bypass validation
- Breaking changes to public API without versioning
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 · 78 lines · 11 tokens per session scan A 9bd86651fcaa
cc-review is a command published in the GitHub repository yeisonrestrepo/code-conductor (17 stars, last pushed today), licensed MIT. It adds 11 tokens to every session and 653 once invoked, about $0.0000 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 2026-08-31.
Other commands, from other repositories
deepen
Spare-budget design pass. Make one shallow module deep — smaller interface, behavior held, tests green before & after.
review
Adversarial senior review of the spec before build. Refute, don't rubber-stamp. Ends in a go/no-go gate.
check
Drift detector. Diff SPEC.md against code. Read-only, zero writes.
fix-comments
Address PR review comments by implementing requested changes automatically.
verify
Perform a systematic second-pass verification of code changes to catch errors before commit.
review
Perform a thorough code review of the current uncommitted changes or a specified file/directory.