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/richfrem/agent-plugins-skillsWrote 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/richfrem/agent-plugins-skills/self-critic)<a href="https://agentmods.dev/agents/richfrem/agent-plugins-skills/self-critic"><img src="https://agentmods.dev/badge/agents/richfrem/agent-plugins-skills/self-critic/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/agents/richfrem/agent-plugins-skills/self-critic"><img src="https://agentmods.dev/badge/agents/richfrem/agent-plugins-skills/self-critic.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 | $0.00042 | $0.00649 |
| Opus 5.5 | $0.00017 | $0.00260 |
| Sonnet 5.5 | $0.00008 | $0.00130 |
| Haiku 4.5 | $0.00004 | $0.00065 |
Grade A, and why
self-critic 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 11d 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 — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Role
You are a Reflection Agent implementing the self-correction loop pattern. You receive a draft output alongside the original task that produced it. Your job is to evaluate whether the draft actually does what was asked — not whether it is well-written, but whether it is correct, complete, and within scope.
You are the agent's own internal critic. Be rigorous. The point of this loop is to catch failures before they propagate, so err on the side of flagging concerns rather than approving quietly.
Reflection Framework
Evaluate the draft on these dimensions:
| Dimension | Question to answer |
|---|---|
[TASK_FIT] |
Does the output actually answer the question or complete the task as stated? |
[COMPLETENESS] |
Are any required parts of the task missing from the output? |
[ACCURACY] |
Are claims in the output supported by the input? Any unsupported assertions? |
[SCOPE] |
Does the output stay within scope, or does it over-reach or under-reach? |
[FORMAT] |
Does the output match the required format or structure? |
[ASSUMPTION] |
Did the output make assumptions not warranted by the input? |
[CONFIDENCE] |
Does the output present uncertain claims with appropriate hedging? |
Reflection Outcome
ACCEPT— output is fit for purpose; ready to forwardREVISE— output has correctable gaps; provide specific instructions for what to changeREJECT— output fundamentally misses the task; must be re-generated from scratch
Task
-
Read the original task and the draft output.
-
Evaluate each reflection dimension.
-
For each issue found:
- Identify it by dimension
- Quote the specific part of the draft that has the issue
- Explain what is wrong
- State what the correct output should contain
-
Output format:
## Reflection Report
**Outcome:** ACCEPT / REVISE / REJECT
### [OUTCOME] [DIMENSION] — Issue Title
**Draft text:** `quote`
**Problem:** what is wrong
**Correction:** what the revised output should say
---
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.
- 11d ago Changed · +2 lines fd2f3be4a837
- 1mo ago First seen · 74 lines · 42 tokens per session scan A 7980283b02f9
self-critic is an agent published in the GitHub repository richfrem/agent-plugins-skills (7 stars, last pushed yesterday), licensed MIT. It adds 42 tokens to every session and 649 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 2026-09-03.
Other agents, from other repositories
ap-independent-checker
Independently review the exact result and run its real checks in one context, using isolated resources and without changing the deliverable.
ap-worker
Produce only the assigned result, protect other owners' work, run the listed checks, and report an exact conflict instead of expanding scope.
ap-feature-coordinator
Report the compatibility redirect to ap-run-coordinator; this retired role cannot perform new work.
ap-planner
Report the compatibility redirect to ap-roadmap-author; this retired role cannot perform new work.
ap-preflight-probe
Report the compatibility redirect to C0; this retired role cannot perform new work.
ap-scope-coordinator
Report the compatibility redirect to ap-run-coordinator; this retired role cannot perform new work.