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 jstoup111/ai-conductor --skill coherence-checkgit clone --depth 1 https://github.com/jstoup111/ai-conductorWrote 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/jstoup111/ai-conductor/coherence-check)<a href="https://agentmods.dev/skills/jstoup111/ai-conductor/coherence-check"><img src="https://agentmods.dev/badge/skills/jstoup111/ai-conductor/coherence-check/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/jstoup111/ai-conductor/coherence-check"><img src="https://agentmods.dev/badge/skills/jstoup111/ai-conductor/coherence-check.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 | $0.05414 |
| Opus 5.5 | $0.00020 | $0.02166 |
| Sonnet 5.5 | $0.00010 | $0.01083 |
| Haiku 4.5 | $0.00005 | $0.00541 |
Grade A, and why
coherence-check 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 14d 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 — 349 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Purpose
Authors .docs/coherence/<plan-stem>.md: a single committed artifact mapping every
intake outcome bullet, every PRD FR (product track), every non-deleted ADR file in the
current spec change set when the coherence gate engages, every story,
and every plan task to its counterpart ids with a per-row verdict. This artifact is the auditable
traceability record the operator (and the land-time coherence validator) reads instead
of trusting self-reported "everything's covered" prose in a spec PR.
Any current-change-set .docs/decisions/adr-* path, including a deletion, engages the ADR
layer. That engagement is distinct from the ADR row pool: deleted ADRs produce no row, so a
deletion-only change has no ADR row to author.
Correctness gate: a row's verdict (covered / gap / fail) is a judgment call, not
a mechanical grep. Mapping and achievability are separate questions: a counterpart can exist while
a criterion still cannot be delivered (§4g). Per the /verify-claims protocol, ground every verdict in the actual
cited text — do not mark a row covered on the assumption that a plausible-looking
counterpart id exists; confirm it against the real artifact file.
1. Tier Rule (M/L only)
Read the spec's tier from .docs/complexity/.
- Tier S: this skill does NOT run. Skip it entirely — same treatment as
architecture-diagram/architecture-review/conflict-check for S tier. No
.docs/coherence/artifact is authored, and the land-time validator does not engage for S-tier specs (Story 13). Do not author a stub file "to be safe" — its mere presence is not required and produces work the S-tier exemption exists to avoid. - Tier M: this skill runs, using the session's default model (no override).
- Tier L: this skill runs, pinned to opus for the dispatch (see Section 2).
2. Model Rule (M = session default, L = pinned opus)
This skill is tier-varying, the same pattern as conflict-check and plan:
- M tier: inherit whatever model the invoking session/step is already running — no pin.
- L tier: pin to opus for this dispatch. Large-tier specs have the widest fan-out of outcomes/FRs/stories/tasks and the highest cost of a missed transitive gap, so the semantic-judging pass needs the deepest reasoning tier.
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.
- 14d ago Changed · -118 lines 2cdc79305f24
- 17d ago Changed · +2 lines 3fc336d82ff4
- 19d ago Changed · +22 lines f67c08979e2d
- 23d ago Changed 6734f9dcfc14
- 26d ago Changed · +7 lines bd6d8dda4325
- 1mo ago Changed · +1 lines 931f4c75b0f2
- 1mo ago Changed · +6 lines 2365d3d00957
- 1mo ago Changed · +9 lines 68f333ff7d2c
- 1mo ago Changed · +6 lines 95651c7a8f77
- 1mo ago First seen · 414 lines · 50 tokens per session scan A c947d2340d6c
coherence-check is a skill published in the GitHub repository jstoup111/ai-conductor (7 stars, last pushed today), licensed Apache-2.0. It adds 50 tokens to every session and 5,414 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
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…