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 agentmods add instructions/epicsagas/epic-harness/agents-mdgit 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/instructions/epicsagas/epic-harness/agents-md)<a href="https://agentmods.dev/instructions/epicsagas/epic-harness/agents-md"><img src="https://agentmods.dev/badge/instructions/epicsagas/epic-harness/agents-md.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 | $0.04491 | $0.04491 |
| Opus 5 | $0.02246 | $0.02246 |
| Sonnet 5 | $0.00898 | $0.00898 |
| Haiku 4.5 | $0.00449 | $0.00449 |
Grade A, and why
epic-harness AGENTS.md 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 today.
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 — 357 lines — stays where its author put it; the contents beside it link to each section on GitHub.
epic-harness
25 skills (9 pipeline + 16 quality) + self-evolving agent harness.
Structure
skills/— 25 skills +_dispatchrouter +_criticreviewerregistry/— Seeding resources (embedded in Rust binary at compile time)presets/— Cold-start skill templatesrules/— Seeded host rule filesscripts/install.js— Plugin bootstrap (SessionStart)
src/— Rust crate; single binary (epic-harness)src/hooks/— Ring 0 automation (guard, polish, observe, resume, snapshot, reflect)src/evolve/— Ring 3 evolution loop
docs/— User-facing documentation and assetsarchitecture.md,quickstart.md,demo/,references/,specs/
integrations/common/—HARNESS.mdembedded into the binary (include_str!), self-seeded to~/.harness/HARNESS.md
Architecture: 4-Ring Model
- Ring 0 (Autopilot): Hooks auto-maintain quality, restore sessions, learn
- Ring 1 (Pipeline): 9 skills that orchestrate multi-step workflows (discover → spec → go → audit → eval → ship, orbit, evolve, team)
- Ring 2 (Quality Gates): 17 skills that auto-trigger on context signals (tdd, debug, secure, threat-model, vuln-scan, triage, verify, etc.)
- Ring 3 (Evolve): Observe → Analyze → Evolve → Gate → Reload self-improvement loop
/orbit — Autonomous Pipeline
Single-command spec-to-PR execution with three entry modes.
flowchart TD
START["/orbit"] --> MODE{"requirement?"}
MODE -->|"unclear"| WAIT["Interactive\nUser runs /discover → /spec"]
MODE -->|"clear + complex"| COUNCIL["Council\n4-Voice Auto-spec"]
MODE -->|"clear + simple"| DIRECT["Direct\nAuto-spec"]
WAIT --> SPEC["Load Approved Spec"]
COUNCIL --> SPEC
DIRECT --> SPEC
SPEC --> GO["Go Phase\nPlan → Execute → Integrate"]
GO --> CHECK["Check Phase\nReview + Audit + Test"]
CHECK -->|"PASS"| SHIP["Ship Phase\nIsolated Test → PR → CI"]
CHECK -->|"WARN"| SHIP
CHECK -->|"FAIL"| RETRY{"retry < 3?"}
RETRY -->|Yes| FIX["Go Fix\nTarget fixes from action items"]
FIX --> CHECK
RETRY -->|No| PAUSE["Pause — User decides"]
PAUSE -->|continue| FIX
PAUSE -->|abort| ABORT["Abort"]
SHIP --> EVOLVE["Evolve\nAuto-analyze session"]
EVOLVE --> DONE["Orbit Complete\nConsolidated Report"]
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.
- today Changed · +15 lines · +238 tokens per session ca7612093217
- 5d ago First seen · 342 lines · 4,253 tokens per session scan A 5695275eeae3
epic-harness AGENTS.md is an instructions file published in the GitHub repository epicsagas/epic-harness (17 stars, last pushed yesterday), licensed Apache-2.0. It adds 4,491 tokens to every session, about $0.0225 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 instructions, from other repositories
ai-dial-core CLAUDE.md
Claude Code instructions for epam/ai-dial-core, covering claude.md, build & run, set credentials via environment variables, build (skip tests) and run all tests.
ai AGENTS.md
AGENTS.md instructions for vercel/ai, covering agents.md, project overview, repository structure, key directories and core package dependencies.
blockrun-mcp AGENTS.md
AGENTS.md instructions for BlockRunAI/blockrun-mcp, covering blockrun mcp, commands, project structure, key dependencies and install in codex.
InvestSkill GEMINI.md
Gemini CLI instructions for yennanliu/InvestSkill, covering investskill — gemini cli setup & usage guide, installation & setup, quick start, navigate to the investskill directory and start gemini cli (loads gemini.md automatically).
technocore-chat AGENTS.md
AGENTS.md instructions for flop-labs/technocore-chat: CI runs exactly these — run them before pushing.
openrouter-mcp-multimodal AGENTS.md
AGENTS.md instructions for stabgan/openrouter-mcp-multimodal, covering agent instructions, before you ship, releasing (read this before publishing), short version and version files (must all match package.json).