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 Ancienttwo/repo-harness --skill repo-harness-issue-flowgit clone --depth 1 https://github.com/Ancienttwo/repo-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/ancienttwo/repo-harness/repo-harness-issue-flow)<a href="https://agentmods.dev/skills/ancienttwo/repo-harness/repo-harness-issue-flow"><img src="https://agentmods.dev/badge/skills/ancienttwo/repo-harness/repo-harness-issue-flow/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/ancienttwo/repo-harness/repo-harness-issue-flow"><img src="https://agentmods.dev/badge/skills/ancienttwo/repo-harness/repo-harness-issue-flow.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 | $0.00121 | $0.01947 |
| Opus 5.5 | $0.00048 | $0.00779 |
| Sonnet 5.5 | $0.00024 | $0.00389 |
| Haiku 4.5 | $0.00012 | $0.00195 |
Grade A, and why
repo-harness-issue-flow 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 2d 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 — 135 lines — stays where its author put it; the contents beside it link to each section on GitHub.
repo-harness-issue-flow
Bot entrypoint. Issue/PR driven development (IPDD). GitHub holds the coordination state. No local plan, task, review or notes file holds task state.
Why this flow works
An orchestrator that sees the whole architecture writes each requirement once, in a GitHub issue, with its module, dependencies and boundaries. A worker then needs only the issue URL to start. The PR and CI record the proof, and every agent and person reads the same state.
The boundary text carries most of the value. A worker that meets an open
question fills it. Over-defensive models fill it with fallbacks, aliases,
dual paths and broad try/catch, so that they cannot be blamed. Every
decision that the issue leaves open turns into permanent code. The
orchestrator therefore makes the decisions in the issue, and the worker
executes them or stops and asks.
Seats, sub-agents and claim roles
A seat is a process seat: the orchestrator, the advisor or a worker. A
sub-agent is an agents/fleet/ role that runs inside a seat process.
The orchestrator calls only the read-only sub-agents gatekeeper,
explorer and deep-reasoner. Writers, root-cause-prover included, and
the Codex cross-review run in seats.
A claim role is the GitHub role that a claim gives: coordinator,
writer, head owner, integrator or acceptor.
| Agent | Suggested model | Claim roles it holds | Never does |
|---|---|---|---|
| Orchestrator | Any host's long-lived top-level session with network access, started from repo-harness seats argv orchestrator |
Coordinator of the parent issue; integrator | Implements a child issue in its own sub-tree; calls a writer sub-agent (fast-worker, deep-worker, root-cause-prover) or runs the Codex cross-review as a sub-agent |
| Gap reviewer | A different model family from the orchestrator, when one is available | None. Comments on the drafts | Rewrites the split or decides scope |
| Worker | Any capable coding model | Writer of one issue or PR slot, dispatched by the coordinator; head owner of its PR | Posts its own claim, widens scope, merges, pushes to another owner's branch |
| Acceptor | A seat holds the acceptor role and can call the gatekeeper sub-agent, the default reviewer. The orchestrator does not review a PR itself; an independent gatekeeper sub-agent of its seat may review a PR that it dispatched. The Codex cross-review and every other review run in another seat. For the High tier, a different model family when available; otherwise a fresh same-family context | Acceptor of one review in one round | Reviews its own code, pushes code |
What ships with it
7 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 2d ago Changed · +10 lines · +4 tokens per session 64f0ee86f151
- 3d ago Changed · +1 lines 847ece51d074
- 4d ago Changed · +4 lines 979b0ab8b665
- 5d ago Changed · +14 lines · -1 tokens per session be9700c19440
- 6d ago First seen · 106 lines · 118 tokens per session scan A 3893c9ba6bc0
repo-harness-issue-flow is a skill published in the GitHub repository Ancienttwo/repo-harness (435 stars, last pushed today), licensed MIT. It adds 121 tokens to every session and 1,947 once invoked, about $0.0005 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 2026-10-31.
repo-harness-issue-flow compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| repo-harness-issue-flowAncienttwo/repo-harness | Skill | 435 | today | MIT | A | 121 | Claude Code |
| merge-strategymarcus/sidecar | Skill | 1.1k | 29d ago | MIT | A | 63 | Claude Code |
| worktree-switchingmarcus/sidecar | Skill | 1.1k | 29d ago | MIT | A | 74 | Claude Code |
| release-sidecarmarcus/sidecar | Skill | 1.1k | 29d ago | MIT | A | 53 | Claude Code |
| releasearcee-ai/nac | Skill | 296 | today | Apache-2.0 | A | 53 | Codex |
| linear-cliPeiiii/nextclaw | Skill | 263 | yesterday | MIT | A | 45 | Claude Code, Codex |
| gh-issuesserejaris/personal-corp-os | Skill | 241 | 3d ago | MIT | A | 104 | Claude Code |