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-discovergit 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-discover)<a href="https://agentmods.dev/skills/cajasmota/grafel/grafel-patterns-discover"><img src="https://agentmods.dev/badge/skills/cajasmota/grafel/grafel-patterns-discover/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/cajasmota/grafel/grafel-patterns-discover"><img src="https://agentmods.dev/badge/skills/cajasmota/grafel/grafel-patterns-discover.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 | $0.00903 |
| Opus 5.5 | $0.00000 | $0.00361 |
| Sonnet 5.5 | $0.00000 | $0.00181 |
| Haiku 4.5 | $0.00000 | $0.00090 |
Grade A, and why
grafel-patterns-discover 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 1mo 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 — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.
grafel-patterns-discover
Standalone agent skill for pattern discovery without doc generation. Use when the user wants a fresh pattern audit of an indexed group but does NOT want /generate-docs to regenerate prose.
This skill is the secondary entry point described by ADR-0018; the primary one is /generate-docs Phases 1 + 4.
When to use this skill
- "Refresh my pattern store."
- "Audit our codebase conventions without touching the docs."
- "Did anything new converge since the last
/generate-docsrun?"
Do NOT invoke this skill on first install when no group is registered, when grafel status reports indexing in progress, or as part of /generate-docs (that path runs its own Phase 1 + 4 already).
Inputs the skill expects
- A registered group resolvable via
grafel_orient (view=me). - An up-to-date
<repo>/.grafel/graph.jsonper repo. If any repo's graph is stale, stop and tell the user to rungrafel rebuild <group>first. - Read access to
<group>/.grafel/patterns.json(the pattern store) andpatterns-config.json(thresholds — defaults applied when absent).
Procedure
Step 1 — Slice the codebase
Dispatch one subagent per top-level module cluster (as returned by grafel_orient (view=clusters)). Each subagent receives:
- Its cluster's entity ID set.
- A read-only copy of the existing pattern store (so it can skip shapes already covered).
Subagents do NOT share state during Step 1.
Step 2 — Per-subagent discovery (Phase 1 in ADR-0018 terms)
Each subagent scans its slice for structural recurrences:
- Group entities of the same kind that share file-path prefix, naming convention, or annotation set.
- If a candidate shape appears ≥
per_subagent_thresholdtimes (default 2) within the slice, emit aPatternCandidateviagrafel_patterns(action=record, as_candidate=true, ...). - Include all observed entities as exemplars in the candidate payload — the coordinator needs the exemplar set for clustering.
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.
- 1mo ago First seen · 73 lines · 0 tokens per session scan A 0cfd47b33640
grafel-patterns-discover is a skill published in the GitHub repository cajasmota/grafel (24 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 903 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
autoreview
Structured code review through the shared OpenClaw agent-skills installation.
omh-code-review
This is an OMH code-review workflow skill, projected for Agent Skills hosts (Claude Code, Codex, Cursor, opencode, OpenClaw, pi).
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
explore-unknowns
Guide the user through a quadrant walk that maps the unknowns of a task — open by listing the known knowns, then work through known unknowns, unknown knowns, and unknown unknowns one stage at a time, ending with a complete four-quadrant map in the user's hands. Use when a request is ambiguous or underspecified, the…
re0-merge
Review and land an external contribution the way this suite does: gate it against the thesis, land it with the author's credit intact, complete a new skill rather than merging it raw, then approve, credit, and explain before closing. Use when reviewing a pull request, as any collaborator or maintainer, not only the…
asplos-writing-style
Use when drafting or revising ASPLOS prose — engineering the first two pages that rapid review actually reads, stating the cross-layer insight as one quotable sentence, structuring per-layer mechanism sections, writing bounded claims, and fitting everything into 11 self-contained pages that include figures and…