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 councilgit 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/council)<a href="https://agentmods.dev/skills/epicsagas/epic-harness/council"><img src="https://agentmods.dev/badge/skills/epicsagas/epic-harness/council/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/epicsagas/epic-harness/council"><img src="https://agentmods.dev/badge/skills/epicsagas/epic-harness/council.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00055 | $0.00830 |
| Opus 5 | $0.00028 | $0.00415 |
| Sonnet 5 | $0.00011 | $0.00166 |
| Haiku 4.5 | $0.00006 | $0.00083 |
Grade A, and why
council 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 9d 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 — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Council — Structured Multi-Voice Decision Making
Iron Law
NO MAJOR DECISION WITHOUT AT LEAST TWO OPPOSING VIEWPOINTS.
When to Trigger
- Architecture choices (monolith vs microservice, SQL vs NoSQL)
- Technology selection (framework, library, language)
- Design decisions with no clear right answer
- Trade-offs between competing requirements (speed vs quality, security vs usability)
- User explicitly requests deliberation
Process
1. Identify the Decision
State the decision in one clear question. Example: "Should we use WebSockets or SSE for real-time updates?"
2. Summon 4 Voices (Parallel)
Launch 4 independent subagents using the Agent tool, each with ONLY the question and relevant context (NOT the full conversation history — this prevents anchoring bias):
| Voice | Role | Focus |
|---|---|---|
| Architect | Long-term correctness | Maintainability, extensibility, architectural alignment |
| Skeptic | Challenge assumptions | Simpler alternatives, hidden costs, "what if we don't?" |
| Pragmatist | Ship it now | Timeline, user impact, operational complexity, team skills |
| Critic | Find the cracks | Edge cases, failure modes, migration risks, rollback difficulty |
Anti-Anchoring Rule: Each voice receives only:
- The decision question
- Relevant codebase context (file paths, current architecture)
- Their role and focus area They do NOT receive: the full conversation, other voices' opinions, or the user's leaning.
3. Synthesize
After all 4 voices report back:
- List areas of agreement (strong signal)
- List areas of disagreement (where trade-offs live)
- Present the user with:
- Recommended option (based on agreement weight)
- Key trade-off (the real decision to make)
- Reversibility (how hard to undo each option)
4. Record Decision
Save the decision to memory:
epic mem add \
--title "Decision: {question}" \
--type decision \
--importance 0.9 \
--body "Context: ...\nOptions: ...\nChosen: ...\nRationale: ...\nTrade-off accepted: ..."
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.
- 9d ago First seen · 83 lines · 55 tokens per session scan A ba506221c1c1
council is a skill published in the GitHub repository epicsagas/epic-harness (18 stars, last pushed today), licensed Apache-2.0. It adds 55 tokens to every session and 830 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
opensrc
Fetch dependency source code to give AI agents deeper implementation context. Use when the agent needs to understand how a library works internally, read source code for a package, fetch implementation details for a dependency, or explore how an npm/PyPI/crates.io package is built. Triggers include "fetch source for"…
lx
Codebase exploration tool that reads many files or whole directories in a single call, with per-file headers, glob include/exclude filters, function/type skeleton extraction (signatures only, no bodies), and head/tail line slicing.
pypi-release
This skill should be used when releasing tunacode-cli to PyPI. It keeps the existing local release checks, then hands the actual PyPI upload to a GitHub Actions workflow that uses the repository's PYPIAPITOKEN secret.
audit-harness
Use when auditing HARNESS.md, pre-commit hooks, pre-push hooks, architecture gates, or CI workflows for tunacode-cli. This skill treats any mismatch, skipped gate, or failing check as a critical failure and requires manual one-by-one execution rather than make targets, batch wrappers, or summary-only audits.
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"…
receive-review
Act on review feedback well — fix real issues, push back on wrong ones. Triggers on address the review, fix the feedback, respond to review, apply review comments.