Borrowing it
Nothing to install: this file belongs to CRJFisher/ariadne. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/CRJFisher/ariadne/main/.claude/skills/reconcile-registry/SKILL.mdgit clone --depth 1 https://github.com/CRJFisher/ariadneWrote 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/crjfisher/ariadne/reconcile-registry)<a href="https://agentmods.dev/skills/crjfisher/ariadne/reconcile-registry"><img src="https://agentmods.dev/badge/skills/crjfisher/ariadne/reconcile-registry/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/crjfisher/ariadne/reconcile-registry"><img src="https://agentmods.dev/badge/skills/crjfisher/ariadne/reconcile-registry.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 | $0.00082 | $0.04754 |
| Opus 5.5 | $0.00033 | $0.01902 |
| Sonnet 5.5 | $0.00016 | $0.00951 |
| Haiku 4.5 | $0.00008 | $0.00475 |
Grade A, and why
reconcile-registry 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 17d 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 — 295 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Reconcile Registry
Reconcile the known-issues registry at
.claude/skills/triage/known_issues/registry.json against work the rest of
the pipeline has already done: fixes that landed in this repo's git log, drift
that triage published, and rules the human elects to make permanent. This
skill is the deliberate, human-invoked step that detects those mechanical
writes and proposes them — the registry's analogue of prioritize.
It owns no logic of its own beyond one orchestration duty — dispatching a
classifier-fixer agent per drift-flagged rule after a --drift apply
(step 4). All registry work runs through one script:
.claude/skills/triage/scripts/reconcile_registry.ts
That script is the only human-invoked writer of registry.json in the
pipeline, and it reaches the registry only through
atomic_update_registry(path, mutator) — one lock-fenced read-mutate-write
per invocation. It never runs on the autonomous sweep: the human is the
registry's sole decider, and this skill exists to make each decision cheap,
never to make it autonomously.
What it detects
The script scans the mechanically-detectable signals and proposes the
corresponding registry write. It never authors rule prose and never makes the
permanent judgment — those stay human creative and judgment work. Beyond the
detected signals, it also accepts directed name-mode flips
(--id ... --fixed --reason, --id ... --promote) where the human names the
rules and the transition rather than letting detection propose it.
| # | Signal (mechanically detected) | Proposed registry write |
|---|---|---|
| 1 | a fix-bearing git log scope in this repo matches a wip rule's backlog_task |
wip → fixed |
| 2 | a published triage_results[].classifier_regressions[] names a rule — its rule_id field carries the registry rule's group_id |
set drift_detected: true; append new drift_evidence[] rows |
| 3 | the human elects to promote a rule (--id <group_id> --promote) |
flip to permanent; regenerate permanent_data.ts |
| 4 | the human retires a rule by name (--id <group_id>... --fixed --reason) |
delete the row(s); unlink their check_*.ts |
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 17d ago First seen · 295 lines · 82 tokens per session scan A c32c02454728
reconcile-registry is a skill published in the GitHub repository CRJFisher/ariadne (23 stars, last pushed 4d ago), licensed MIT. It adds 82 tokens to every session and 4,754 once invoked, about $0.0003 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 2026-10-06.
Other skills, from other repositories
migrate-oxlint
Guide for migrating a project from ESLint to Oxlint. Use when asked to migrate, convert, or switch a JavaScript/TypeScript project's linter from ESLint to Oxlint.
tree-sitter-language-pack-extracting-code-structure
Use when the user wants structured code metadata from a source file — functions, classes, imports, exports, symbols, docstrings, comments, or syntax diagnostics. Covers ts-pack process feature flags, the JSON result shape, and the default feature set.
tree-sitter-language-pack-parsing-source
Use when the user wants a tree-sitter syntax tree for a source file — an s-expression dump or JSON tree. Covers ts-pack parse, language auto-detection vs --language, stdin input, and reading haserrors.
webiny-api-logger-catalog
Name: Logger Import: import { Logger } from "webiny/api/logger" Source: @webiny/api-core/features/logger/index.ts Description: Structured logging with multiple log levels.
detect-ssr-leak
Detect server-side memory leaks in Node.js SSR services. Use when user asks to "check for memory leak", "detect leak", "SSR memory leak", "memory leak", or wants to diagnose growing memory usage on a Node.js server. TRIGGER when user mentions memory leak detection, especially for SSR/Vue/React server-side rendering.
frigg-first-code-search
Default to Frigg MCP instead of shell rg/grep/find/fd/cat/sed for source-code discovery, search, navigation, and proof reads in attached repos. Scenario-first routing: pick the flow, then the tool. Shell remains correct for git, build/test output, generated/unindexed paths, explicit live-disk checks, and when Frigg is…