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 cajasmota/grafel --skill grafel-patterns-syncgit clone --depth 1 https://github.com/cajasmota/grafelWrote 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/cajasmota/grafel/grafel-patterns-sync)<a href="https://agentmods.dev/skills/cajasmota/grafel/grafel-patterns-sync"><img src="https://agentmods.dev/badge/skills/cajasmota/grafel/grafel-patterns-sync.svg" alt="Measured on agentmods" 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 | $0.01079 |
| Opus 5 | $0.00000 | $0.00540 |
| Sonnet 5 | $0.00000 | $0.00216 |
| Haiku 4.5 | $0.00000 | $0.00108 |
Grade A, and why
grafel-patterns-sync 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 6d 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 — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.
grafel-patterns-sync
Bidirectional sync between the per-group pattern store and a repo's version-controlled CLAUDE.md / AGENTS.md. Marker-wrapped, idempotent, and privacy-aware.
This skill is the export-side surface described by ADR-0018. Privacy boundary: any anti-pattern with private=true MUST NOT be written to a version-controlled file, regardless of which direction the sync is running.
When to use this skill
- "Update CLAUDE.md with our latest patterns."
- "Pull patterns from this repo's CLAUDE.md into the store."
- "Reconcile CLAUDE.md and the pattern store."
Do NOT invoke this skill if no patterns have been recorded yet (run /generate-docs or /grafel-patterns-discover first), or if the user has manually edited the marker-wrapped block — surface the edits as candidates first via the import path.
Marker block format
The sync block lives inside this pair of HTML-comment markers (matching the gfleet upsertAgentRulesBlock convention established in AI-Memory):
<!-- grafel:patterns:start v=1 -->
... pattern index ...
<!-- grafel:patterns:end -->
Content outside the markers is user territory and is preserved byte-for-byte.
The block is a SHORT INDEX, not the full pattern markdown. Each pattern entry is a one-liner:
- **<trigger>** — confidence <c>, <n> observations. [Full recipe](docs/patterns/<category>/<id>.md)
The full recipe lives at the linked path (written by /generate-docs Phase 6). A human reading CLAUDE.md can click through; an agent reading the block has every trigger summarised in one place.
Inputs
- The target
CLAUDE.md/AGENTS.mdfile path (per-repo, version-controlled). - The group name (defaults to the registered group when only one exists).
- The current pattern store, loaded via
grafel_patterns(action=query, include_candidates=false)or via the CLI's direct file read.
Procedure
Step 1 — Resolve the file
If the file does not exist, the skill creates it containing only the marker block. If it exists with no markers, the block is appended after a blank-line separator. If it exists with markers, the block contents are replaced; everything outside the markers is preserved.
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.
- 6d ago First seen · 86 lines · 0 tokens per session scan A 55b5783403c4
grafel-patterns-sync is a skill published in the GitHub repository cajasmota/grafel (12 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,079 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…
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…