What is awesomeharness?

A context-light procedure for structured coding work in repositories that use the awesomeharness workflow.

Routing repository searches, checking whether existing code can be reused, splitting work into units, running builders and auditors, fixing findings, and recording completion proof.

It keeps implementation grounded in repository evidence, defined goals, independent review, verification, and saved progress.

awesomeharness — Skill for Claude Code and Codex by roarista

Install

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.

Any agent

npx skills add roarista/awesome-harness --skill awesomeharness

Clone the repo

git clone --depth 1 https://github.com/roarista/awesome-harness

Made for: Claude Code, Codex.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/roarista/awesome-harness/awesomeharness/github.svg)](https://agentmods.dev/skills/roarista/awesome-harness/awesomeharness)

Your own site

<a href="https://agentmods.dev/skills/roarista/awesome-harness/awesomeharness"><img src="https://agentmods.dev/badge/skills/roarista/awesome-harness/awesomeharness/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/roarista/awesome-harness/awesomeharness"><img src="https://agentmods.dev/badge/skills/roarista/awesome-harness/awesomeharness.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 24 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 581 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00024	$0.00581
Opus 5.5	$0.00010	$0.00232
Sonnet 5.5	$0.00005	$0.00116
Haiku 4.5	$0.00002	$0.00058

Measured 15d ago against content hash 473004f1ff3c, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

awesomeharness 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 15d 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.

codex/skills/awesomeharness/SKILL.md · 20 lines

What it actually says

Args = resume point; else STATE_CURRENT.md, no archives. Delegation: CLAUDE.md/AGENTS.md (router/pins). Scoped reads; ml search if needed; ~/.claude/tools/l1.py and ~/.claude/tools/skeleton.py before bodies. Graphify structure, Semgrep AST, rg text. Load specs/skills/MCPs only as needed.

Run python3 ~/Downloads/awesome-harness/tools/state-distiller.py . --budget. Prune (<=5 min): move detail, keep pointers/history. Only propose global/out-of-scope changes.
Ponytail first. Prove REUSE/ADAPT/REJECT on live files; STOP if covered.
Spec: CONTEXT / REUSE / CHANGE / GOAL / VERIFY. GOAL = end state/exclusions; VERIFY = fallible commands/pass criteria. Orchestrator owns FILE PLAN; builders stop/report unplanned files or budget overruns.
One routed builder/unit; no concurrent siblings in dirty trees. Without subagents, build/self-audit. Subagents get core rules from SubagentStart hook; don't paste into specs.
Distinct routed auditor, same spec: CRITICAL: loss/security/secrets/money. HIGH: normal path wrong/invented API/unmet GOAL. MEDIUM: edge input/I/O/risky untested branch/test cannot fail. LOW: style. VERDICT: REJECT for CRITICAL/HIGH, MEDIUM in money/auth/secrets/data-loss/prod data, or missing/failing VERIFY. PASS WITH FIXES for other MEDIUM/LOW; PASS only <=LOW. Fix every item; re-audit rejects. Check tree/output; reports are claims.
Unit + repo check-all, real output. Commit scoped; ml record; .now.md (NOW/LAST_VERIFIED/NEXT <=5 lines), STATE resume; push. Handoff: $compact-prep then /clear.

Satisfy ~/Downloads/awesome-harness/docs/quality-gates.md; TS before handoff: trellis audit . --json --baseline .artifacts/trellis/baseline.json (exit 2 rejects); trellis guide cleanup to fix. Reports: .artifacts/agent-reports/.md; return <=8 lines: verdict/change/proof/risk/next/path; no logs/diffs/code. One final summary.

Never: source >200 lines (old cap 300; shrink touched; bypass needs Ro's yes); erase unrelated dirty work via force/reset/clean/stash/restore; unauthorized spend, prod mutation, messages/destruction.

Changes

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.

15d ago Changed · -24 lines · -10 tokens per session 473004f1ff3c
16d ago Changed · +6 lines 2d8a42d5d9f0
1mo ago Changed · -45 lines · -25 tokens per session a5ca67160730
1mo ago Changed · +42 lines ef2113b9ec74
2mo ago First seen · 41 lines · 59 tokens per session scan A 4b411970978d

Subscribe to this mod's changes

awesomeharness is a skill published in the GitHub repository roarista/awesome-harness (1 stars, last pushed 4d ago), licensed MIT. It adds 24 tokens to every session and 581 once invoked, about $0.0001 per session on Opus 5.5. 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.

Building agents

awesomeharness next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
awesomeharnessroarista/awesome-harness	Skill	1	4d ago	MIT	A	24	Claude Code, Codex
imagegenopenai/codex	Skill	134k	today	Apache-2.0	A	113	Codex
playwright-climicrosoft/playwright	Skill	99k	today	Apache-2.0	A	19	Claude Code
local-ai-agentsmicrosoft/ai-agents-for-beginners	Skill	79k	today	MIT	A	200	Claude Code, Codex
systematic-debuggingobra/superpowers	Skill	314k	3d ago	MIT	A	21	Claude Code
next-cache-components-adoptionvercel/next.js	Skill	143k	yesterday	MIT	A	95	Claude Code
next-partial-prefetching-adoptionvercel/next.js	Skill	143k	yesterday	MIT	A	103	Claude Code