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 skyf0xx/hedgehog --skill hedgehog-contributinggit clone --depth 1 https://github.com/skyf0xx/hedgehogWrote 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/skyf0xx/hedgehog/hedgehog-contributing)<a href="https://agentmods.dev/skills/skyf0xx/hedgehog/hedgehog-contributing"><img src="https://agentmods.dev/badge/skills/skyf0xx/hedgehog/hedgehog-contributing/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/skyf0xx/hedgehog/hedgehog-contributing"><img src="https://agentmods.dev/badge/skills/skyf0xx/hedgehog/hedgehog-contributing.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 MCP Rug Pull · line 28 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
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 | $0.00118 | $0.01350 |
| Opus 5.5 | $0.00047 | $0.00540 |
| Sonnet 5.5 | $0.00024 | $0.00270 |
| Haiku 4.5 | $0.00012 | $0.00135 |
Grade A, and why
hedgehog-contributing 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 — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Contributing to Hedgehog
Walks a user from "I want to fix/build this in Hedgehog itself" to an open
pull request against skyf0xx/hedgehog. This is for changes to the
discipline — src/agents/, src/skills/, src/templates/,
bin/cli.mjs, README.md — never for changes to the user's own project,
which is a different repo with different rules.
When this runs
- The user names a specific gap (a bug they hit, a roadmap item) and wants to fix it in Hedgehog rather than work around it locally.
tweakeroffered this at the end of a build and the user said yes.
If the user hasn't picked a target yet, browse issues labeled
roadmap
with them and let them choose one — prefer an issue also labeled
good-first-issue for a first contribution, since those are scoped to one
file or one narrow addition.
Before starting
Confirm where the Hedgehog source actually lives on this machine. A project
that ran npx @skyf0xx/hedgehog init has a copy of the payload
(.claude/agents/, .claude/skills/), not the Hedgehog repo itself —
editing those files changes nothing upstream. Ask the user:
- If they already have a local clone of
skyf0xx/hedgehog, use it. - If not, offer to clone it:
gh repo fork skyf0xx/hedgehog --clone(forks under their account and clones the fork), orgit clone https://github.com/skyf0xx/hedgehogif they'd rather push directly to a branch on a repo they already have write access to.
Do this in a separate directory from the user's own project — never inside it.
Writing the issue or PR
Use the pr-writing skill for style: brief, info-dense, Simplified
Technical English, only verified claims. Most of Hedgehog's inbound queue
is read first by inbound-triage, an agent, before a human ever sees it —
the same register inbound-triage uses when it comments back (see that
skill's "Comment style" section) — so write plainly for both readers at
once.
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 Changed · -2 tokens per session 1b17e5a23617
- 1mo ago First seen · 99 lines · 120 tokens per session scan A 56007dc24eb7
hedgehog-contributing is a skill published in the GitHub repository skyf0xx/hedgehog (46 stars, last pushed yesterday), licensed MIT. It adds 118 tokens to every session and 1,350 once invoked, about $0.0005 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 2026-08-30.
Other skills, from other repositories
quality-gates
Graduated pre-commit quality checks that scale with project complexity and user tier. Level 0 for Builder-tier small projects, up to Level 4 for enterprise codebases. Thresholds configurable in architecture.md.
using-git-worktrees
Create isolated workspaces via git worktrees for parallel development. Safety verification ensures worktree directories are gitignored before use.
finishing-a-development-branch
5-step branch completion workflow — verify tests, determine base branch, present merge options, execute, and clean up.
sprint-end
Use when the user wants to ship a sprint's work to main via PR.
merge-down
Use when the user is inside a parallel stream (worktree branch) and wants to bring that branch up to date with the LATEST of its parent branch — typically after one or more sibling streams have merged their work up into the parent (via /merge-up). Pulls the parent's accumulated commits down into the current branch…
merge-up
Use when the user is inside a parallel stream (worktree branch) and wants to merge that branch's committed work into the parent branch it was created from, then bring the stream back up to date with the parent. True merge (keeps individual commits); prompts before pushing the parent. Pairs with /parallel-work, which…