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 H2Sxxa/spec-coding-skills --skill spec-crlpgit clone --depth 1 https://github.com/H2Sxxa/spec-coding-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/h2sxxa/spec-coding-skills/spec-crlp)<a href="https://agentmods.dev/skills/h2sxxa/spec-coding-skills/spec-crlp"><img src="https://agentmods.dev/badge/skills/h2sxxa/spec-coding-skills/spec-crlp/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/h2sxxa/spec-coding-skills/spec-crlp"><img src="https://agentmods.dev/badge/skills/h2sxxa/spec-coding-skills/spec-crlp.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 | $0.00081 | $0.01368 |
| Opus 5 | $0.00041 | $0.00684 |
| Sonnet 5 | $0.00016 | $0.00274 |
| Haiku 4.5 | $0.00008 | $0.00137 |
Grade A, and why
spec-crlp 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.
How it starts
The opening of the file, as written. The whole thing — 138 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Spec Correction Loop
Use this skill when implementation already exists and feedback shows a mismatch between expected and actual behavior.
This skill is about converging on correct behavior with evidence. Start from the spec, reproduce the problem, find the root cause, make the smallest coherent fix, and verify the result. Treat lint, tests, logs, CI, and review comments as signals that help narrow the gap between the implementation and the acceptance criteria.
Repository preference override
Before starting the correction loop, look for a SPEC.md in the target repository root.
If it exists, treat it as the repository-specific preference layer for:
- validation commands and validation order
- setup and environment expectations
- knowledge-base location for durable findings
- cross-skill workflow conventions
If it is missing, use the built-in defaults for this skill series instead of blocking on the missing file.
If it is partial, use the fields it defines and fall back to defaults for the rest.
Built-in defaults
When no repository root SPEC.md is available, use these defaults:
- validation behavior: prefer discoverable repository tooling; if no validation commands are discoverable, say validation is not configured yet
- knowledge-base location:
docs/knowledge-base/ - context retrieval: query
spec-indexfor similar symptoms, root causes, fix patterns, setup gotchas, and validation rules before correction work
Core responsibilities
- Reconstruct the expected behavior from the current spec, acceptance criteria, or user request.
- Compare the expected behavior with actual behavior using concrete evidence.
- Trace failures to a root cause instead of patching symptoms.
- Apply focused fixes and re-run the most relevant checks.
- Surface reusable lessons that should be captured by
spec-index.
Context retrieval before correction
Before starting a correction loop, retrieve relevant memory through spec-index.
Look for:
- similar symptoms or error messages
- prior root causes
- reusable fix patterns
- setup or environment gotchas
- validation rules and known flaky checks
- component-specific pitfalls
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 · 138 lines · 81 tokens per session scan A d5d901be317d
spec-crlp is a skill published in the GitHub repository H2Sxxa/spec-coding-skills (3 stars, last pushed 1mo ago), licensed MIT. It adds 81 tokens to every session and 1,368 once invoked, about $0.0004 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
browser-edge-cases
SOP for debugging browser automation failures on complex websites. Use when browser tools fail on specific sites like LinkedIn, Twitter/X, SPAs, or sites with Shadow DOM.
ios-simulator
Verify and debug native, React Native, Expo, or Flutter apps on an iOS Simulator with agent-device. Use when an agent needs to launch an app, inspect its live UI, tap, type, scroll, validate a code change, collect failure evidence, or reproduce a workflow on an iPhone or iPad Simulator.
debugging-executions
Debug failed or wrong-output workflow executions using executions tools. Load when the user reports execution failures, unexpected node output, empty parameter values after a successful run, or a node showing a red or failed expression error.
atmos-schemas
JSON Schema for Atmos: stack-manifest and atmos.yaml config schemas, IDE auto-completion, validate stacks/schema/config, SchemaStore integration.
issue
Use when starting a chain from a GitHub issue — turning an issue URL or number into a triaged, planned, dispatched, and reviewed pull request. Classifies the thread (bug → root-cause discipline, feature → plan chain, question → drafted reply), synthesizes a spec from the issue's own acceptance criteria, then runs the…
therapeutic-ifs
Unified inner work engine: Schema deconstruction (diagnosis) + IFS therapy (treatment). Absorbs: schema-deconstruction.