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 hariharapanigrahy/layerkit --skill layerkit-fix-from-dry-rungit clone --depth 1 https://github.com/hariharapanigrahy/layerkitWrote 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/hariharapanigrahy/layerkit/layerkit-fix-from-dry-run)<a href="https://agentmods.dev/skills/hariharapanigrahy/layerkit/layerkit-fix-from-dry-run"><img src="https://agentmods.dev/badge/skills/hariharapanigrahy/layerkit/layerkit-fix-from-dry-run/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/hariharapanigrahy/layerkit/layerkit-fix-from-dry-run"><img src="https://agentmods.dev/badge/skills/hariharapanigrahy/layerkit/layerkit-fix-from-dry-run.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 | $0.00030 | $0.00500 |
| Opus 5 | $0.00015 | $0.00250 |
| Sonnet 5 | $0.00006 | $0.00100 |
| Haiku 4.5 | $0.00003 | $0.00050 |
Grade A, and why
layerkit-fix-from-dry-run scanned grade A with 1 finding 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 9d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- Vendor docs/OpenAPI/curl evidence How it starts
The opening of the file, as written. The whole thing — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.
layerkit-fix-from-dry-run
Use this skill when an integration change fails verification. The failure may come from a client test, build, typecheck, linter, mocked vendor call, or reviewer finding.
Inputs
- Failing command output or reviewer finding
- Edited source files and tests
- Current maps/proposals if the client uses them
- Vendor docs/OpenAPI/curl evidence
- Customer datalayer/interface evidence
Protocol
- Reproduce or inspect the failure.
- Identify the exact source path responsible.
- Re-open the vendor/customer evidence for the failing dimension.
- Prefer deleting or rewriting stale code over adding another wrapper.
- Patch the real package file or test directly.
- Validate explicit map/proposal artifacts only when they are part of the change:
layerkit proposal validate ./proposal.json
layerkit map validate ./map.json
- Re-run the client package verification command.
- If evidence is exhausted and the semantic answer is still unclear, stop with a residual human question.
Common Fixes
- Vendor field renamed: update the existing mapping to write the new vendor field from the existing client field.
- Vendor field removed: delete the old mapping and assertions.
- Vendor added required data already present in the client datalayer: map it directly and add/adjust tests.
- Vendor added required data missing from the client datalayer: leave a TODO at the integration point and call it out in handoff.
- Shape changed from scalar to object: update the existing mapper and tests from the new schema, preserving client naming.
Forbidden
- Inventing field names or defaults to silence a test.
- Adding a parallel adapter when the existing adapter can be changed.
- Writing
.layerkit/outartifacts as a substitute for source edits. - Asking a deterministic CLI command to infer a semantic fix from prose.
- Leaving old broken code in place and adding new code around it.
Success Criteria
- Root cause tied to evidence or an explicit residual gap.
- Existing source/tests were updated or stale code was deleted.
- New files/functions/exports list what they replace.
- Client verification passes, or the remaining blocker is documented for a human.
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.
- 9d ago First seen · 57 lines · 30 tokens per session scan A b5562764b19c
layerkit-fix-from-dry-run is a skill published in the GitHub repository hariharapanigrahy/layerkit (8 stars, last pushed 1mo ago), licensed MIT. It adds 30 tokens to every session and 500 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
remediate-failures
Correct failures, rule violations, and acceptance criteria gaps detected during QA review. Activate when qa-review returns FAIL. Fixes without redefining scope — loops until all quality gates pass.
verify
Verify that a change really works before you claim completion.
reality-verification
This skill should be used when the user asks to "verify a fix", "reproduce failure", "diagnose issue", "check BEFORE/AFTER state", "VF task", "reality check", "check test quality", "mock-only tests", or needs guidance on verifying fixes by reproducing failures before and after implementation, or detecting mock-heavy…
flutter-skill
Automate and test Flutter applications — launch apps, inspect widgets, tap elements, enter text, scroll, swipe, take screenshots, validate state, and debug via Dart VM Service Protocol. Use when the user wants to run Flutter app tests, automate Flutter UI interactions, inspect widget trees, debug a running Flutter…
debugging
Playwright test debugging conventions for the scaffold — reading failure messages, classifying failure modes (TimeoutError, ZodError, strict-mode violation, locator not found, network errors, schema drift), the playwright.config.ts capture defaults (trace on-first-retry, screenshot only-on-failure, video…
Debugging Strategies
Advanced debugging patterns for test failures covering root cause analysis, flakiness investigation, performance debugging, and systematic troubleshooting methodologies.