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 Ridwannurudeen/hermes-council --skill adversarial-critiquegit clone --depth 1 https://github.com/Ridwannurudeen/hermes-councilWrote 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/ridwannurudeen/hermes-council/adversarial-critique)<a href="https://agentmods.dev/skills/ridwannurudeen/hermes-council/adversarial-critique"><img src="https://agentmods.dev/badge/skills/ridwannurudeen/hermes-council/adversarial-critique/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/ridwannurudeen/hermes-council/adversarial-critique"><img src="https://agentmods.dev/badge/skills/ridwannurudeen/hermes-council/adversarial-critique.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 | $0.00032 | $0.01117 |
| Opus 5 | $0.00016 | $0.00558 |
| Sonnet 5 | $0.00006 | $0.00223 |
| Haiku 4.5 | $0.00003 | $0.00112 |
Grade A, and why
adversarial-critique 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 12d 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 — 150 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Adversarial Critique
Use council_evaluate, council_review_plan, council_review_diff, and council_preflight to stress-test work before it goes live. The council's adversarial structure surfaces blind spots that self-review misses.
When to Use
- Before publishing: Evaluate research, articles, or analysis
- Before deploying: Gate code deployments with safety review
- Before sending: Review messages or communications for tone and accuracy
- During development: Get structured feedback on design decisions
- After completion: Retrospective quality check on finished work
Tools
council_evaluate -- Quality Assessment
council_evaluate(
content="[your work product]",
question="[what task it was supposed to accomplish]",
criteria=["accuracy", "depth", "falsifiability", "evidence"]
)
Returns per-persona feedback and an overall confidence score.
council_gate -- Safety Check
council_gate(
action="Deploy v2.0 to production with new authentication system",
risk_level="high",
context="New auth uses JWT tokens instead of session cookies. All tests pass."
)
Returns verdict (allow, allow_with_conditions, or deny), blocking risks, required checks, safe alternatives, and reasoning. Uses abbreviated council (Skeptic + Oracle + Arbiter) for speed.
Risk level thresholds:
low: Allowed if confidence >= 30%medium: Allowed if confidence >= 50%high: Allowed if confidence >= 70%
council_review_plan -- Plan Review
council_review_plan(
plan="[implementation plan]",
objective="Ship the feature without breaking existing integrations",
risk_level="medium"
)
council_review_diff -- Diff Review
council_review_diff(
diff="[git diff]",
objective="Review for bugs, security regressions, and missing tests",
files=["src/auth.py", "tests/test_auth.py"]
)
council_preflight -- Action Gate
council_preflight(
action="Run production migration",
risk_level="high",
context="Migration backfills NULL emails before adding NOT NULL",
checks=["backup exists", "rollback SQL written"]
)
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.
- 12d ago First seen · 150 lines · 32 tokens per session scan A 4254bd5c81ec
adversarial-critique is a skill published in the GitHub repository Ridwannurudeen/hermes-council (50 stars, last pushed 4mo ago), licensed MIT. It adds 32 tokens to every session and 1,117 once invoked, about $0.0002 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
autoreview
Pre-commit/ship code review: Codex default; optional Claude or Pi.
omh-code-review
This is a Hermes-native code-review workflow skill.
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
code-reviewer
Code review specialist focused on patterns, bugs, security, and performance.
full-repo-review
Comprehensive four-wave review of all repo source files, producing a prioritized issue backlog.
agent-teams-simplify-and-harden
Implementation + audit loop using parallel agent teams with structured simplify, harden, and document passes. Spawns implementation agents to do the work, then audit agents to find complexity, security gaps, and spec deviations, then loops until code compiles cleanly, all tests pass, and auditors find zero issues or…