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 rtazima/claude-proj-blueprint --skill incoherence-detectorgit clone --depth 1 https://github.com/rtazima/claude-proj-blueprintWrote 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/rtazima/claude-proj-blueprint/incoherence-detector)<a href="https://agentmods.dev/skills/rtazima/claude-proj-blueprint/incoherence-detector"><img src="https://agentmods.dev/badge/skills/rtazima/claude-proj-blueprint/incoherence-detector/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/rtazima/claude-proj-blueprint/incoherence-detector"><img src="https://agentmods.dev/badge/skills/rtazima/claude-proj-blueprint/incoherence-detector.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 | $0.00000 | $0.00872 |
| Opus 5 | $0.00000 | $0.00436 |
| Sonnet 5 | $0.00000 | $0.00174 |
| Haiku 4.5 | $0.00000 | $0.00087 |
Grade A, and why
incoherence-detector 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 — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Incoherence Detector
Activated when: "check consistency", "find mismatches", "incoherence", "specs match code", "docs outdated", "sync check", "drift".
Purpose
Detect mismatches between three layers:
- Specs — What we said we'd build (PRDs, API specs, schemas)
- Docs — What we say it does (CLAUDE.md, README, ADRs, runbooks)
- Code — What it actually does (source files, tests, config)
Workflow
Phase 1: Inventory (gather sources)
For the target module/feature, collect:
- PRD in
docs/product/ - Relevant ADRs in
docs/architecture/ - API spec in
docs/specs/api/(if applicable) - CLAUDE.md sections mentioning the module
- README.md sections mentioning the module
- Source files implementing the feature
- Test files covering the feature
- .env.example entries (if applicable)
- Runbooks referencing the feature
Phase 2: Cross-reference (find mismatches)
Check each pair:
Spec <> Code:
- Features listed in PRD but not implemented
- Features implemented but not in any PRD
- API endpoints in spec but missing from code
- API endpoints in code but missing from spec
- Data models in spec vs actual schema/types
- Acceptance criteria in PRD vs test coverage
Docs <> Code:
- Commands documented but not working
- Commands working but not documented
- Env vars in code but missing from .env.example
- Env vars in .env.example but unused in code
- Module map in CLAUDE.md vs actual file structure
- Gotchas in CLAUDE.md vs actual behavior
- Architecture in ADRs vs current implementation
Spec <> Docs:
- PRD requirements not reflected in docs
- Docs describing features not in any PRD
- Version/status mismatches (PRD says "planned", docs say "done")
- Naming inconsistencies between PRD and docs
Phase 3: Classify findings
For each mismatch found:
- DRIFT — Code evolved past the spec. Spec needs updating.
- MISSING — Spec/doc promises something not yet implemented.
- STALE — Documentation describes old behavior.
- CONFLICT — Two sources contradict each other.
- ORPHAN — Implementation exists with no spec or doc.
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 · 94 lines · 0 tokens per session scan A d20ce1db348e
incoherence-detector is a skill published in the GitHub repository rtazima/claude-proj-blueprint (20 stars, last pushed 3mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 872 tokens. 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
printing-press-output-review
Internal sub-skill: agentic review of a printed CLI's sampled command output for plausibility issues that rule-based checks can't encode (substring-match relevance, format bugs, silent source drops, ranking failures). Invoked via the Skill tool by the main printing-press skill at Phase 4.85 and printing-press-polish…
systemic-issue-triage
Trigger: new issue, bug report, triage, backlog, issue flood, community report, root cause, dead-end, blocked user. Attack issues by root class, never one-by-one; fixes must shrink the system, not grow it.
issue-root-resolution
Trigger: root audit, atacar la raíz, issue roots, backlog roots, mechanism map, deletion-driven fix, resolver issues de raíz, close outdated issues. Audit and resolve issue clusters by verified root cause.
rdd-defect-workflow
Trigger: RDD, receipt-driven development, review authority, receipt/lineage, correction/recovery, delivery gate/kill switch, bounded review defects. Guide work.
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"…
truecourse-analyze
Run TrueCourse architecture analysis on this repository.