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 agentmods add skills/fazxes/claude-code/writing-rulesnpx skills add fazxes/Claude-code --skill writing-rulesgit clone --depth 1 https://github.com/fazxes/Claude-codeWhat 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 | $0.00052 | $0.02255 |
| Opus 5 | $0.00026 | $0.01128 |
| Sonnet 5 | $0.00010 | $0.00451 |
| Haiku 4.5 | $0.00005 | $0.00226 |
Grade D, and why
writing-hookify-rules scanned grade D with 2 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 2d 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.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
chmod\s+777 Matches: chmod 777, chmod 777 Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
rm\s+-rf Matches: rm -rf, rm -rf The source is not reproduced here
No licence file
A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.
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.
- 2d ago First seen · 375 lines · 52 tokens per session scan D 2994b5d31522
writing-hookify-rules is a skill published in the GitHub repository fazxes/Claude-code (233 stars, last pushed 5mo ago), with no licence file. It adds 52 tokens to every session and 2,255 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it D with 2 findings (asks for root, recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
chores
Run the standard pre-ship wrap-up for the current work — verify suite, code review, docs sync, then commit and open a PR. Trigger on "/chores", "run chores", "wrap up", "ship it", or when a task is done and should ship.
review
Code-review the current branch's diff for correctness bugs and Swarm-invariant violations. Trigger on "/review", "review my changes", "code review", or before shipping. Reports findings; does not auto-fix.
pr
Open a pull request from the current worktree — verify green, commit scoped, push, and write the PR from the actual diff. Trigger on "/pr", "open a PR", "make a pull request".
design-review
Review dashboard/UI changes for design-system and usability consistency. Trigger on "/design-review", "review the UI", or after editing packages/web. Reports findings; does not auto-fix.
plan
Show the Swarm development plan as clean markdown tables — milestones, what's done, in progress, and next. Trigger on "/plan", "show the plan", "where are we", "what's next", "status", or any request for a progress snapshot.
gm-skill
Plugkit-served instruction stream. Three-layer admission (cost, bounds, direction) over every mutation. Closure on first emit; partial = non-monotonic.