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 extend-conventiongit 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/extend-convention)<a href="https://agentmods.dev/skills/cajasmota/grafel/extend-convention"><img src="https://agentmods.dev/badge/skills/cajasmota/grafel/extend-convention/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/extend-convention"><img src="https://agentmods.dev/badge/skills/cajasmota/grafel/extend-convention.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Rogue Agent · line 74 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
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 | $0.01556 |
| Opus 5 | $0.00000 | $0.00778 |
| Sonnet 5 | $0.00000 | $0.00311 |
| Haiku 4.5 | $0.00000 | $0.00156 |
Grade A, and why
extend-convention 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 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.
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 — 124 lines — stays where its author put it; the contents beside it link to each section on GitHub.
extend-convention
Add a new stack convention for the generate-docs skill. Run when the user has a repo whose framework or runtime is not covered by any existing file under skills/generate-docs/conventions/.
When to use this skill
- The user said in Pass 0 of
generate-docsthat none of the listed conventions match their repo. - The user explicitly asks: "Add a convention for
<stack>." - A
generate-docsrun aborted at Pass 0 with the message: "stack X has no convention; runextend-convention."
The CLI surface (per grafel's CLI plan) for invoking this skill is:
grafel conventions add <stack>
The CLI command creates a stub convention file at ~/.claude/skills/generate-docs/conventions/<stack>.md and then triggers this skill to fill it. If the CLI is unavailable, the user can place a stub manually and invoke this skill directly.
Inputs
- The target stack name (e.g.,
flask,nestjs,gin,nextjs-app-router). - A path to the stub file the agent will fill.
- A path to a reference codebase (the user's repo) that uses the stack.
- The skill always reads
_graph-searchability.mdand two existing conventions for structural reference. Pick the two most similar:- For a new Python framework: read
django.mdandfastapi.md. - For a new Node framework: read
react.mdandnodejs-generic.md. - For a new infra stack: read
infra-cdk.mdandinfra-terraform.md. - For a new mobile stack: read
react-native.mdand one web equivalent. - Otherwise: read
generic.mdand the closest match.
- For a new Python framework: read
Procedure
Step 1 — Internalize structure
Read the universal convention _graph-searchability.md first, then the two reference conventions. Note their section order — it is not negotiable. Every convention follows the same shape:
- Required reading callout.
- Public surface (numbered list).
- Module shape (with directory tree).
- Entry points (Pass 3).
- Dynamic edges (Pass 4).
- Deployment signals (Pass 5).
- Manifest files (Pass 5 —
dependencies.md). - Cross-cutting pitfalls.
- Cross-repo signals.
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 · 124 lines · 0 tokens per session scan A 6cdc62421f8e
extend-convention is a skill published in the GitHub repository cajasmota/grafel (14 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,556 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…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…