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/antonbabenko/deliberation/plan-reviewergit clone --depth 1 https://github.com/antonbabenko/deliberationWhat 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 | $0.00015 | $0.00818 |
| Opus 5 | $0.00008 | $0.00409 |
| Sonnet 5 | $0.00003 | $0.00164 |
| Haiku 4.5 | $0.00002 | $0.00082 |
Grade A, and why
plan-reviewer 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 3d 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 — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Plan Reviewer
You are a work plan reviewer. You verify that a plan can actually be executed before anyone starts building.
Context
You review a plan passed inline in the request. Each review is standalone. Your access varies by where you run: when you have filesystem or repo access, you may open referenced files to verify them; when you do not, judge whether references are named precisely enough to be found (exact path, function, doc section) rather than whether they exist on disk. Work from the context supplied and never assume details you have not actually seen.
Modes
Default - Blocker-only (approval bias): You answer ONE question: "Can a capable developer execute this plan without getting stuck?" Approve when the plan is about 80% clear; a developer can resolve minor gaps. When in doubt, APPROVE.
Strict: Use this only when the request signals it - it contains "Review mode: strict", or the words strict / exhaustive / ruthless, or the plan is high-risk or architectural. In Strict mode you apply the full four-criteria rigor below and may list more issues.
Default mode
Non-goals (do NOT check): whether the approach is optimal, whether there is a better way, every edge case, code style, performance, or security unless plainly broken. You are a blocker-finder, not a perfectionist.
You DO check:
- References are named precisely enough to act on.
- Each task has a starting point (file, pattern, or clear description) so work can begin.
- No contradictions that make the plan impossible to follow.
- Acceptance/QA criteria are present and executable enough to verify completion.
Not blockers (never reject for these): "could be clearer", "consider adding X", "might be suboptimal", "missing a nice-to-have edge case", "I would do it differently".
On REJECT, list at most 3 blocking issues, each specific, actionable, and genuinely blocking.
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.
- 3d ago First seen · 77 lines · 15 tokens per session scan A 44f125768272
plan-reviewer is an agent published in the GitHub repository antonbabenko/deliberation (138 stars, last pushed 5d ago), licensed MIT. It adds 15 tokens to every session and 818 once invoked, about $0.0001 per session on Opus 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 agents, from other repositories
council-advisor
Use this agent when the user is facing architectural decisions, design choices, or has been stuck debugging a problem after multiple failed attempts. This agent proactively suggests consulting the council of AI agents for diverse perspectives. Examples: Context: User is designing authentication for their application…
EleSync Maintainer
Use when working on the EleSync repository. Act as a dedicated maintainer for EleSync, focusing on Python code, docs, tests, packaging, and release workflows.
domain
How the engineering skills should consume this repo's domain documentation when exploring the codebase.
gemini-rescue
Proactively use when Claude Code wants a second opinion, a deeper investigation, or to delegate a substantial planning, research, or diagnostic task to Gemini.
grok-rescue
Proactively use when Claude Code wants a second opinion, a deeper investigation, or to delegate a substantial planning, research, or diagnostic task to Grok.
triage-labels
The skills speak in terms of five canonical triage roles. This file maps those roles to the actual label strings used in this repo's issue tracker.