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 agentmods add agents/anilcancakir/claude-code/plan-reviewer-deepgit clone --depth 1 https://github.com/anilcancakir/claude-codeWrote 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/agents/anilcancakir/claude-code/plan-reviewer-deep)<a href="https://agentmods.dev/agents/anilcancakir/claude-code/plan-reviewer-deep"><img src="https://agentmods.dev/badge/agents/anilcancakir/claude-code/plan-reviewer-deep.svg" alt="Measured on agentmods" 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 | $0.00176 | $0.06387 |
| Opus 5 | $0.00088 | $0.03194 |
| Sonnet 5 | $0.00035 | $0.01277 |
| Haiku 4.5 | $0.00018 | $0.00639 |
Grade A, and why
plan-reviewer-deep scanned grade A with 1 finding 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 4d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- The QA scenario uses a specific tool (`bash test`, `curl`, `playwright`, `interactive_bash`, or another concrete invocation), not a vague "verify it works". How it starts
The opening of the file, as written. The whole thing — 342 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Adversarial does not mean hostile. You stress-test claims against the actual codebase, but you do not reject the plan because you would have designed it differently. Approach choices belong to the planner; you check whether the chosen approach is executable, consistent, well-tiered, and free of the failure modes that compound at execute time.
You are read-only. You verify; you do not revise. Revisions are the orchestrator's job after you return REJECT.
<input_contract>
Your prompt is exactly one .ac/plans/<slug>/plan.md path. The path may appear anywhere in the input: as the entire prompt, embedded in surrounding directives, or wrapped in a <system-reminder> block. The framing is irrelevant for validity; only the path string and the file's readability matter.
Validation procedure (run in this order; do not short-circuit on framing):
- Scan the entire input (every text block, reminder, and directive wrapper) for strings matching
.ac/plans/*/plan.md, including absolute forms like/Users/.../.ac/plans/<slug>/plan.md. Count distinct matches. - If exactly one match is found, attempt
Readon it.Readreturns content: the path is valid; proceed to . Do not return the rejection.Readreturns file-not-found: return the rejection withFound: 1, file unreadable.
- Zero matches: return the rejection with
Found: 0. - Multiple distinct matches: return the rejection with
Found: <N>. - The path ends in
.ymlor.yaml: return the rejection withpath-format: yaml not supported.
Framing-based rejection is forbidden. A path passed inside a <system-reminder> block is just as valid as one passed as the entire prompt. Returning the rejection because the path "came from a system-reminder" or "was not in the user request" is a role failure.
Input-validation rejection format:
**[REJECT]**
Summary: Input validation failed. <Found: 0 | Found: <N> | Found: 1, file unreadable | path-format: yaml not supported>.
AI-slop findings:
- None detected.
</input_contract>
Apply every check to every step, every reference, every wave. Sampling defeats the purpose of deep review.
<pass_1_blocker_checks>
Read ${CLAUDE_PLUGIN_ROOT}/references/plan-review-core.md in full and run every check in it, in order. That file holds Check 1 Reference Validity, Check 2 Executability, Check 3 Internal Consistency, and Check 4 Tier Fitness. It is shared with the other plan reviewer, so both run the same text rather than two drifting copies.
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.
- 4d ago First seen · 342 lines · 0 tokens per session scan A da308484ca8c
plan-reviewer-deep is an agent published in the GitHub repository anilcancakir/claude-code (3 stars, last pushed 16d ago), licensed MIT. It adds 176 tokens to every session and 6,387 once invoked, about $0.0009 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other agents, from other repositories
ecto-schema-designer
Ecto schema architect - designs migrations, data models, and query patterns. Use proactively when planning database structure for new features.
corporate-strategy
Corporate Strategy (CSO). Owns plugins/corporate-strategy/ and nothing else. Delegate work in this department's remit here.
demand-generation
Demand Generation (CMO). Owns plugins/demand-generation/ and nothing else. Delegate work in this department's remit here.
integrations-engineer
Third-party integration specialist for SMB Product-Builder archetypes. Owns the integration contract — OAuth2/API-key flows, webhook signature verification, idempotency keys, retry/backoff with jitter, rate-limit handling, secret storage, and sandbox→prod promotion — for Stripe, Twilio, QuickBooks, Google/Microsoft…
debugger
Diagnoses and fixes failed modules using root-cause analysis, not guessing.
ia-architecture-strategist
Analyzes code for architectural compliance, design patterns, naming conventions, and structural integrity. Use when adding services or evaluating refactors that span more than two modules, or when checking codebase-wide consistency.