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 waqas1412/claude-harness --skill orchestrategit clone --depth 1 https://github.com/waqas1412/claude-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/waqas1412/claude-harness/orchestrate)<a href="https://agentmods.dev/skills/waqas1412/claude-harness/orchestrate"><img src="https://agentmods.dev/badge/skills/waqas1412/claude-harness/orchestrate/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/waqas1412/claude-harness/orchestrate"><img src="https://agentmods.dev/badge/skills/waqas1412/claude-harness/orchestrate.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 | $0.00050 | $0.03280 |
| Opus 5.5 | $0.00020 | $0.01312 |
| Sonnet 5.5 | $0.00010 | $0.00656 |
| Haiku 4.5 | $0.00005 | $0.00328 |
Grade A, and why
orchestrate 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 16d 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 — 218 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/orchestrate: run the lenses in one loop
The lenses are checklists, not agents. This skill names which ones apply to a given change, what each one asks, and what evidence closes it. You apply them yourself in this loop: you plan, you read, you edit, you run lint and build and tests, and you review your own diff before committing.
How this works: read the lens, or dispatch it
The 16 lens files in ~/.claude/agents/*.md are both the lens CONTENT and real dispatch targets. The
same directory also holds implementer.md, which is a writer, not a lens. Two ways to run a lens,
chosen per lens:
- Read it and apply it here. Cheapest, and right for a small diff, or when the lens needs context this conversation already holds. Read the matching file and use its rubric as the checklist.
- Dispatch it as a subagent. Right when an independent read is worth the round trip: a large or risky change, or a verdict you do not want coloured by the reasoning that produced the code. A reviewer in a fresh context cannot see this conversation, so name the target (diff, PR, branch, or planned change) and the baseline it answers to. Nothing more: the lens carries its own rubric, and a checklist of what you already suspect narrows it into agreeing with you. Do not hand it your findings or tell it which part to focus on.
Either way the verdict is yours. A dispatched lens returns findings, never a decision, and a finding is not true until you have checked it against the code yourself.
Every verdict follows one shape: read references/findings-contract.md before reporting anything. It
defines the precision-versus-recall dial, the required failure_scenario, the three-way verdict, the
report cap, and the disclosure rule. It is the same contract Claude Code's own code-review uses.
Pick the lenses, then say which you skipped
Right-size to the change:
- One-file fix: correctness and repo-fit only.
- Feature or multi-file change: add the two or three lenses the change actually touches.
- Cross-cutting, shared-seam, or architecture change: the full panel.
What ships with it
1 file 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.
- 16d ago Changed · +47 lines · -42 tokens per session ae102ee95b36
- 1mo ago First seen · 171 lines · 92 tokens per session scan A 71c5d8096a7c
orchestrate is a skill published in the GitHub repository waqas1412/claude-harness (2 stars, last pushed 17d ago), licensed MIT. It adds 50 tokens to every session and 3,280 once invoked, about $0.0002 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.
Other skills, from other repositories
validate
Use when operating as the Fabrik Validate stage agent. This skill guides final validation of an implementation, verifying requirements are met, tests pass, and the PR is ready to merge.
review
Use when operating as the Fabrik Review stage agent. This skill guides code review of an implementation, finding and fixing issues, and ensuring the PR is ready for human review.
review-comment
Use when operating as the Fabrik Review comment reviewer. This skill guides applying user decisions on review findings — fixing issues, dismissing false positives, or deferring items — then committing and pushing without signaling stage completion.
coding-quality-loop
Use when a coding agent must turn a software goal, bug, issue, or refactor into a small, verified, independently reviewed code change.
forge-code-review
Forge code-review method — order, severity levels, Codex handoff. Use before any commit or when asked to review code — code review, check my code, PR review, before I commit.
gh-pr
Create, review, or manage GitHub pull requests. Use when asked to open, check, or merge a PR.