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 puristajs/harness --skill reflective-criticgit clone --depth 1 https://github.com/puristajs/harnessWrote 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/puristajs/harness/reflective-critic)<a href="https://agentmods.dev/skills/puristajs/harness/reflective-critic"><img src="https://agentmods.dev/badge/skills/puristajs/harness/reflective-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/skills/puristajs/harness/reflective-critic"><img src="https://agentmods.dev/badge/skills/puristajs/harness/reflective-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 | $0.00022 | $0.00089 |
| Opus 5 | $0.00011 | $0.00044 |
| Sonnet 5 | $0.00004 | $0.00018 |
| Haiku 4.5 | $0.00002 | $0.00009 |
Grade A, and why
reflective-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 10d 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.
What it actually says
Reflective Critic
Attack drafts before publication. Flag unsupported claims, missing evidence, contradictions, unconsidered alternatives, weak citations, and overconfident language.
Do not rewrite the final answer unless asked. Return precise issues and the smallest changes needed to make the output reliable.
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.
- 10d ago First seen · 14 lines · 22 tokens per session scan A 8b39b928cf7a
reflective-critic is a skill published in the GitHub repository puristajs/harness (5 stars, last pushed 3d ago), licensed Apache-2.0. It adds 22 tokens to every session and 89 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 2026-08-31.
Other skills, from other repositories
reviewing-changes
Use when a review package asks you to review a plan step's change set (todo.startReview): you are the REVIEWER, not the author. How to judge an agent-written diff, file findings with addreviewcomment, and settle with exactly one reviewverdict.
reflecting-findings
Use when a reflection package hands you another agent's review findings to verify (before they become a fix request): you are the REFLECTOR, an independent skeptic. Judge each finding against the real code and settle it with reflectfinding — kept or refuted.
review-code
Read code. Understand it. Find issues. Report clearly.
assignment-review
A review skill for checking submitted Python, Go, code explanations, debugging notes, or practice exercises.
check-vercel-rules
Explicit Codex workflow: Run the packaged Vercel Labs agent-skills rule audit on the current project.
code-review
Comprehensive code review for security, performance, and best practices.