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 epicsagas/epic-harness --skill _criticgit clone --depth 1 https://github.com/epicsagas/epic-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/epicsagas/epic-harness/_critic)<a href="https://agentmods.dev/skills/epicsagas/epic-harness/_critic"><img src="https://agentmods.dev/badge/skills/epicsagas/epic-harness/_critic.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 5.1 | $0.00057 | $0.00761 |
| Opus 5 | $0.00028 | $0.00380 |
| Sonnet 5 | $0.00011 | $0.00152 |
| Haiku 4.5 | $0.00006 | $0.00076 |
Grade A, and why
_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 7d 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 — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Critic — Adversarial Proposal Review
In-loop vs out-of-band. epic-harness forbids external LLM calls from production, so the reflect loop ships a deterministic critic (
src/evolve/critic.rs) that gates seeding when reward hacking is suspected. THIS skill is the out-of-band LLM version a meta-agent or human runs during/evolvereview for the cases the deterministic check cannot catch (non-local effects, manifest/evidence nuance).
When to Trigger
- During
/evolvereview of newly seeded skills - When
reward_hacking_suspectedis true in metrics - After a seesaw-regression round, before re-proposing
Process
1. Gather the proposal + evidence
- Read the evolved skill proposal(s) from this round
- Read the EditManifest (edit_type, target, intended_effect, predicted_impact)
- Read the round's TaskDigests (outcome, failure_categories, evidence_excerpts)
- Read recent score_history dimension_averages (tool_success, output_quality, execution_cost)
2. Falsify the manifest (paper §4.3, Table 9)
For each proposal, ask: does the trace evidence support the predicted_impact?
- If the manifest claims "Lift avg_score_with" but output_quality is regressing → Reject
- If the manifest claims a tool fix but the implicated component shows no change → Warn
- If the evidence corroborates the predicted effect → Approve
3. Reward-hacking cross-check
- Is execution_cost rising while output_quality falls across the window?
- Could the skill be gaming a metric (fewer tool calls inflating cost score) rather than improving outcomes?
- If yes, the skill must NOT ship — flag for the rejected buffer.
4. Non-local effect scan
- Will this skill's guard rules conflict with existing skills (overlapping triggers, contradictory rules)?
- Does it interact with shared state (context, memory, control) in a way the manifest didn't account for?
Anti-Rationalization
| Excuse | Rebuttal | Do instead |
|---|---|---|
| "The score went up, so it works" | Score can rise via metric gaming | Verify the outcome improved, not just the score |
| "The seesaw passed, it's safe" | Seesaw is coarse; sub-threshold coupling evades it | Check dimension deltas, not just aggregate pass |
| "It's just a prompt tweak" | Prompt edits have non-local effects on shared context | Trace the effect across skills, not just the target |
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.
- 7d ago First seen · 62 lines · 57 tokens per session scan A 9b3d06ca041c
_critic is a skill published in the GitHub repository epicsagas/epic-harness (18 stars, last pushed 2d ago), licensed Apache-2.0. It adds 57 tokens to every session and 761 once invoked, about $0.0003 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 skills, from other repositories
toxic-senior-reviewer
Code review in the voice of a toxic senior developer — dry sarcasm without profanity, no fluff, no empty praise. Use this skill whenever the user asks for a code review, says "how can I improve this", "what do you think of this code", "take a look at this", "rate this solution", "critique this", "do a code review"…
request-review
Prepare work for review so a reviewer can verify it fast and fairly. Triggers on get this reviewed, ready for review, request a review, hand off for review.
review
Review code for bugs, quality, and correctness. Triggers on review, check, audit, verify requests.
code-reviewer
Reviews a working diff for correctness, not style.
steelman-then-break
Pressure-test a design proposal or technology choice in two separated passes: first the strongest possible case FOR it (steelman — argue the best version, even stronger than the author put it), then a rigorous case AGAINST it (red-team — name the anti-pattern, lead with what breaks first, cite the team's prior scars)…
code-simplify
Reduce complexity and improve readability WITHOUT changing behavior. Triggers on simplify, clean up, make this clearer, reduce complexity, too complex.