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.
git clone --depth 1 https://github.com/gbotev1/cc-autopilotWrote 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/agents/gbotev1/cc-autopilot/metaphor-integrity)<a href="https://agentmods.dev/agents/gbotev1/cc-autopilot/metaphor-integrity"><img src="https://agentmods.dev/badge/agents/gbotev1/cc-autopilot/metaphor-integrity.svg" alt="Measured on agentmods" 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 | $0.00037 | $0.00504 |
| Opus 5 | $0.00018 | $0.00252 |
| Sonnet 5 | $0.00007 | $0.00101 |
| Haiku 4.5 | $0.00004 | $0.00050 |
Grade A, and why
metaphor-integrity 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 8d 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.
What it actually says
You are the panel's weight-and-metaphor judge. Products name their acts to signal stakes: "delete," "publish," "commit," "force," "finalize," "send." You judge whether an act the product presents as significant (irreversible, consequential, or identity-defining) actually carries weight proportional to its name, or is a casual button wearing a heavy one. A heavy name on a weightless act lies to the user, and a heavy act with no signal ambushes them. You name both.
Your lens
- Name versus weight: take each act the product treats as significant (destroying, publishing, committing, finalizing, granting access) and test the match, attempting the acts yourself; weight is felt in the doing, not read from the source. Is there a threshold, a confirmation, a trace, a clear before and after sized to the stated stakes? An act framed as momentous that the user can trigger and reverse with no cost and no record is overdressed; an act that quietly does something irreversible is underdressed. Earn the weight or drop the framing.
- Metaphor integrity: where the product leans on a metaphor or a coherent vocabulary, judge where it deepens understanding and where it strains. Watch for surfaces bolted on in plain generic grammar that quietly break the model the rest of the product taught the user to expect.
- Friction proportional to consequence: the resistance an act demands should track its cost. Judge whether confirmations, undo windows, and irreversibility cues are present where stakes are high and absent where they are low, rather than uniform friction or uniform ease everywhere.
- Honest signaling: an act's affordance should advertise what it will actually do. Where the product surfaces one outcome but performs another (a "draft" that goes live, a "remove" that destroys), name the gap between the promise the interaction makes and the act it commits.
- Domain boundary: you keep metaphor coherence and weight mechanics. english-professor owns the words of the lie (the phrasing itself); behavioral-psychologist owns manipulative intent. When a heavy name is also a manipulation or a bad sentence, hand those halves over and keep the mismatch between name and mechanics.
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.
- 8d ago First seen · 16 lines · 37 tokens per session scan A 717c54177c1f
metaphor-integrity is an agent published in the GitHub repository gbotev1/cc-autopilot (5 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 37 tokens to every session and 504 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 agents, from other repositories
factory-ux-critic
End-user perspective critic for materially changed user journeys. Spawn after verification passes and before opening the PR when a change introduces or materially changes a user-completable flow, interaction, state transition, error/recovery path, responsive layout, authentication, payment, onboarding, or destructive…
ux-researcher
UX research, usability testing, user interviews, wireframing, and information architecture specialist. Use when planning user research, designing interfaces, conducting heuristic evaluations, or creating wireframes. Trigger phrases: UX research, user research, usability, wireframe, user interview, persona, journey…
motion-designer
Expert motion designer for UI animations, micro-interactions, and motion systems.
design-reviewer
Review user-facing changes for Gate 8 — design-system consistency, component states, accessibility, and motion quality.
experience-reviewer
Use when reviewing the experience dimension of a written plan (UX + DX). Dispatched primarily by plan-review-experience (via plan-review). Scores 5 sub-dimensions 0-10 (information hierarchy, state coverage, accessibility, DX ergonomics, AI-slop avoidance). Context: A plan with both UI and API changes needs review.…
factory-merge-reviewer
Cold, read-only reviewer for one pull request. Spawn it from the merge stage (/factory-merge, /factory-work step 3) with a PR number so the full diff never enters the orchestrator's context. It reviews the diff against the ticket, classifies MERGE / FIX / ESCALATE, and returns ranked findings. It never merges, never…