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 | $0.00092 | $0.02380 |
| Opus 5 | $0.00046 | $0.01190 |
| Sonnet 5 | $0.00018 | $0.00476 |
| Haiku 4.5 | $0.00009 | $0.00238 |
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 10d 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 — 171 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: one loop, no dispatch
The 16 files in ~/.claude/agents/*.md are the lens CONTENT. When a checklist below is not enough
detail for the change in front of you, Read the matching file and use its rubric. They are reference
documents here, never dispatch targets. Do not spawn a subagent or author a workflow to run a lens
unless the user asks for that in the moment.
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.
Declare skips out loud ("no design parity: this diff has no UI"). A silent skip reads as a pass.
Set the dial: precision or recall
Decide before you start, and say which. Getting it backwards fails in both directions.
- Precision (default; a small diff, a nit pass, anything about to go to a reviewer): only findings a
maintainer would act on. Cap at
min(files_changed, 4). A repo-wide sweep prompted by a diff-scoped nit is this dial set wrong. - Recall (an audit, a large or risky change, or when asked to be thorough): catch every real bug a careful reviewer would catch in one sitting. Real bugs matter more than false positives here, so err on the side of surfacing.
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.
- 10d ago First seen · 171 lines · 92 tokens per session scan A 71c5d8096a7c
orchestrate is a skill published in the GitHub repository waqas1412/claude-harness (1 stars, last pushed 3d ago), licensed MIT. It adds 92 tokens to every session and 2,380 once invoked, about $0.0005 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
fabrik-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.
fabrik-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.
fabrik-validate-comment
Use when operating as the Fabrik Validate comment reviewer. This skill guides updating the validation report, re-running checks, and applying minor fixes in response to user feedback — signaling completion only when the user explicitly indicates the issue is resolved.
fabrik-implement-comment
Use when operating as the Fabrik Implement comment reviewer. This skill guides applying user-requested code changes during implementation, committing and pushing, and updating the task checklist — without signaling stage completion.
review-loop
Run the adversarial verification loop — implement, then hand the change to a fresh checker that did not write it, fix what it finds, and re-dispatch until APPROVE. Use before claiming any behavioural change is done, and on requests like "review loop", "adversarial review", "independent review", "get this verified"…
no-mistakes
Validate committed feature-branch changes through the no-mistakes pipeline: intent, rebase, review, test, docs, lint, push, PR, and CI. Use when the user asks to run no-mistakes, ship safely, validate before pushing, or gate a change before it reaches upstream.