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 bouob/agent-harness --skill agent-harness-sprintgit clone --depth 1 https://github.com/bouob/agent-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/bouob/agent-harness/agent-harness-sprint)<a href="https://agentmods.dev/skills/bouob/agent-harness/agent-harness-sprint"><img src="https://agentmods.dev/badge/skills/bouob/agent-harness/agent-harness-sprint/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/bouob/agent-harness/agent-harness-sprint"><img src="https://agentmods.dev/badge/skills/bouob/agent-harness/agent-harness-sprint.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 | $0.00044 | $0.00879 |
| Opus 5 | $0.00022 | $0.00439 |
| Sonnet 5 | $0.00009 | $0.00176 |
| Haiku 4.5 | $0.00004 | $0.00088 |
Grade A, and why
agent-harness-sprint 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 — 118 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Harness Sprint
Run a Codex-oriented Planner -> Generator -> Evaluator sprint. Use this skill for complex work that benefits from planned delegation and a verification gate.
References
../../references/codex-sprint-contract.md- Codex sprint artifact contract and task rules../../references/codex-config-schema.md- Codex model routing config
Step 1 - Resolve Codex Model Routing
Read Codex config in this order:
./.codex/agent-harness.local.json~/.codex/agent-harness.json- Built-in defaults from
../../references/codex-config-schema.md
Only read .codex config files. Do not read .claude/agent-harness*.json.
Resolve each role independently:
plannerevaluatorgenerator.codegenerator.writegenerator.researchgenerator.collect
Routing rules:
mode: "inherit"- omit bothmodelandreasoning_effortwhen spawning that rolemode: "explicit"- passmodel; ifreasoning_effortis present, pass it too
If the config has an unknown host, version, mode, or malformed explicit route, warn the user and fall back that role to inherit-mode routing for this run.
If Codex rejects a configured model or reasoning override at runtime, warn the user, retry that role with inherit-mode routing, and continue unless the retry also fails.
Step 2 - Planning Gate
If the user provided only a loose spec, first use the planning behavior from agent-harness-sprint-plan.
Continue to execution only when the plan has:
- Acceptance criteria
- A task list
- Ownership boundaries
- Verification commands or checks
- Routing notes that state which tasks inherit the current session and which use explicit model or reasoning overrides
Step 3 - Initialize Artifacts
Use .sprint/<YYYYMMDD-HHmmss>/ for local sprint artifacts.
Create:
sprint-meta.jsonsprint-plan.mdsprint-progress/
Keep .sprint/ local-only. Do not commit sprint artifacts unless the user explicitly asks.
Step 4 - Execute Generator Tasks
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 · 118 lines · 44 tokens per session scan A 96eef3f95cb8
agent-harness-sprint is a skill published in the GitHub repository bouob/agent-harness (5 stars, last pushed 1mo ago), licensed MIT. It adds 44 tokens to every session and 879 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 2026-08-31.
Other skills, from other repositories
pr-check
PR review compliance: fetch review comments from an open PR, categorize as resolved/unresolved/dismissed, critically evaluate fixable items, implement approved fixes, and reply inline. Pass --unattended to halt on human-judgment items (emitted as Pending-Human) instead of prompting via AskUserQuestion.
ci-review
CI-optimized code review: multi-agent parallel review with confidence scoring and atomic GitHub PR review posting. Runs specialized review agents, scores findings, and submits a GitHub PR review via post-review.sh. Always executes post-review.sh to submit a review on every run (including zero-findings runs). Triggers…
council
Consult external AI council (Gemini 3.8 Flash, Codex, GLM-5.3, Kimi) for thorough reviews and consensus-driven decisions. Use ONLY when explicitly invoked with "/council" or when user says "consult the council", "invoke council", or "council review". Do NOT auto-trigger on generic phrases like "thorough review".
babysit
PR babysitter: monitors CI status, auto-rebases when behind, auto-fixes CI where possible, delegates review comment handling to dlc:pr-check, and re-requests review after fixes. Designed for /loop usage with Remote Control.
brainstorm
You MUST use this skill before /pm when work is ambiguous, scope is unclear, or multiple approaches exist. Explores problem space, proposes 2-3 approaches with trade-offs, and produces an approved spec document that feeds into both issue creation (/pm) and implementation planning (/cdt). Triggers: brainstorm, explore…
pr-validity
PR validity analysis: fetch PR diff, extract new code additions, search existing codebase for duplicate or overlapping implementations, classify changes, and create a structured GitHub issue.