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 smixs/disruptor-skills --skill spawning-reviewersgit clone --depth 1 https://github.com/smixs/disruptor-skillsWrote 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/smixs/disruptor-skills/spawning-reviewers)<a href="https://agentmods.dev/skills/smixs/disruptor-skills/spawning-reviewers"><img src="https://agentmods.dev/badge/skills/smixs/disruptor-skills/spawning-reviewers/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/smixs/disruptor-skills/spawning-reviewers"><img src="https://agentmods.dev/badge/skills/smixs/disruptor-skills/spawning-reviewers.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 | $0.00102 | $0.03643 |
| Opus 5 | $0.00051 | $0.01821 |
| Sonnet 5 | $0.00020 | $0.00729 |
| Haiku 4.5 | $0.00010 | $0.00364 |
Grade A, and why
spawning-reviewers 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 11d 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 — 131 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Spawning Reviewers
Stage contract
- Stage: 5a. Review (inside the build loop) · Kind: method
- Inputs: a settled artifact to critique (frozen — no edits while the review runs).
- Outputs: ranked findings anchored to precise locations — no verdict.
- Entry gate: called each review-and-fix iteration by the
converging-and-polishingskill. - Done when: located findings returned from a cross-family / independent critic (unanchored claims don't count).
- Next: back to the
converging-and-polishingskill — you fix the real findings, verify, re-spawn.
Overview
A review's value is decided before the reviewer starts working — by how you framed the prompt, which reviewers you picked, and whether you forced them to examine the real thing. Get those wrong and even a strong model returns confident noise.
Core principle: a reviewer is an instrument you can bias or starve without noticing. Tell it what you expect — or even where to look — and it confirms your priors. Don't make it look at the artifact and it reviews your description of the artifact. Pick reviewers that share a brain and their agreement means nothing. This skill is the discipline that prevents all three.
When to use
- You want a genuine critique, not reassurance, on anything that "works but might be wrong/bloated/fragile."
- A high-stakes or hard-to-reverse decision deserves an independent perspective.
- A previous review felt thin, agreeable, or suspiciously aligned with what you already believed.
When NOT to use: trivial or throwaway artifacts; when you need help producing rather than critiquing; when a 30-second self-check settles it.
The two failure modes (the heart of the skill)
1. Leading the witness — biased framing
Anything in the prompt that signals what you expect or where to look gets echoed back. Poison includes:
- a changelog / history ("here's what changed", "after N rounds of fixes")
- a list of suspected problems or "I think X is the issue"
- pointing at a region — or assigning a sub-area to "focus on / go deepest on". Even a neutral-sounding "go deep on the auth module" partitions the artifact and caps what the reviewer hunts for. Coverage is not a reason to pinpoint (see Principle 3 for the real fix).
- enumerating the artifact's parts. A feature/module list in the prompt reads as an exhaustive set — the model treats it as the whole and stops thinking past it. Point at the artifact; do not list it.
- calibrating the outcome ("should be clean", "few findings expected")
- asking for a pass/fail verdict instead of findings
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.
- 11d ago First seen · 131 lines · 102 tokens per session scan A cecd7ad8e8ef
spawning-reviewers is a skill published in the GitHub repository smixs/disruptor-skills (18 stars, last pushed 2mo ago), licensed MIT. It adds 102 tokens to every session and 3,643 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 2026-08-30.
Other skills, from other repositories
debug
Run /debug to find and fix a bug's root cause: a test failing for an unclear reason, /check verify finding a failure, or behavior being wrong. Runs a reproduce, localize, hypothesize, test, fix, verify loop, makes the minimal fix, and hands a regression test to /test. No features, no extra refactors.
todos
This chat has a shared, live TODO plan — your tasks for the conversation, which the user also edits. Read this skill and reach for the todo tools whenever a request takes more than a couple of steps. It covers the plan model (group = task, items = its steps; loose items are the user's lane), how to work it: propose…
writing-workflow-skills
Use when adding a new workflow skill to pi-thinkrail-workflow, changing an existing workflow skill's role, trigger, handoff, or structure, or checking a workflow skill against the workflow system's rules. Not for authoring general-purpose skills outside this package.
setting-up-a-project
Use whenever asked to set up, onboard, initialize, or spec a project — the front door when the workspace has no spec graph yet (brand-new or an existing codebase); also seeded by the app's Set-up-project card (/skill:setting-up-a-project). Not for feature work in an already-specced project — use the brainstorming…
writing-specs
Use when a workflow step drafts or revises a spec artifact — a goal-and-requirements, an architecture, or a module SPEC — or when a workflow skill names it at such a step. The shared quality bar for specs — not a workflow, nothing to execute.
animate
Build a web animation: whether it should animate at all, the purpose, the tool, the properties, the easing curve, the duration, interruption and exit. Writes the CSS or Motion code for dropdowns, modals, toasts, tooltips, accordions, press feedback, stagger and scroll reveals. Use to animate something or make a…