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/nick-railsback/skill-engine/clean-cachenpx skills add nick-railsback/skill-engine --skill clean-cachegit clone --depth 1 https://github.com/nick-railsback/skill-engineWhat 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 | $0.00057 | $0.02139 |
| Opus 5 | $0.00028 | $0.01069 |
| Sonnet 5 | $0.00011 | $0.00428 |
| Haiku 4.5 | $0.00006 | $0.00214 |
Grade C, and why
clean-cache scanned grade C with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
rm -rf -- "$cache_root"/git-managed/*/ "$cache_root"/web-doc/*/ How it starts
The opening of the file, as written. The whole thing — 187 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Clean cache
Opt-in destructive command. Deletes the persistent local clone cache that DISCOVER and REFRESH populate under ~/.cache/skill-engine/. Always dry-runs first; only deletes after explicit user confirmation.
Usage
/skill-engine:clean-cache [kind]
kind is optional:
- omitted → clean every cache subtree under
~/.cache/skill-engine/, including old flat-layout entries. git-managed→ clean only~/.cache/skill-engine/git-managed/.web-doc→ clean only~/.cache/skill-engine/web-doc/.
Always prompts with a list of directories before deletion. No deletion happens without confirmation.
What gets deleted
Everything under ${XDG_CACHE_HOME:-$HOME/.cache}/skill-engine/. The cache is partitioned by source kind:
~/.cache/skill-engine/git-managed/<source_id>-<sha>/— shallow clones of git-backed upstream sources at a specific SHA.~/.cache/skill-engine/web-doc/<source_id>-<crawl_id>/— snapshots of crawled web documentation for a specific crawl.
Old flat-layout entries (~/.cache/skill-engine/<source_id>-<sha>/) may still exist if they predate the kind-partitioned layout and have not yet been migrated by REFRESH; this command will clean them too. The cache is regenerable: a subsequent DISCOVER or REFRESH against the same upstream re-creates whatever it needs from gh/git or the web crawler.
Nothing outside the cache root is touched. No contextualizer state (.claude/skills/<slug>-context/, including its research/ and references/ directories) is touched. No user files outside ~/.cache/skill-engine/ are touched.
Workflow
cache_root="${XDG_CACHE_HOME:-$HOME/.cache}/skill-engine"
if [ ! -d "$cache_root" ]; then
printf '%s\n' "Cache root not present at $cache_root — nothing to clean."
exit 0
fi
# Parse optional [kind] argument.
kind="${1:-}"
case "$kind" in
""|git-managed|web-doc) ;;
*)
printf 'ERROR: invalid kind %q (expected: git-managed, web-doc, or omitted)\n' "$kind" >&2
exit 2
;;
esac
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 · 187 lines · 57 tokens per session scan C 56f3b5629cdc
clean-cache is a skill published in the GitHub repository nick-railsback/skill-engine (2 stars, last pushed 25d ago), licensed MIT. It adds 57 tokens to every session and 2,139 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
skill-creator
Create or improve Zhin Agent skills (SKILL.md). Use when asked to add a skill, write SKILL.md, document a repeatable agent workflow, or refine skill frontmatter/keywords. Triggers: 创建技能, 写 SKILL, skill-creator, 加 skill.
skill-sync-checker
Detects content drift between skill files and their source documents. Helps maintain skills that are derived from other documentation by comparing content and flagging outdated sections.
tech-design-generation
Generates professional Technical Design Documents following industry-standard engineering practices. This skill activates when the user asks to write a technical design, create an architecture design, draft a design doc, write a technical proposal, do system design, create a technical design document, write an RFC…
test-cases-generation
Generates structured test case sets with multi-dimensional coverage from project code analysis or specification documents. This skill activates when the user asks to write test cases, generate tests, supplement tests, create test coverage, or improve test completeness. It auto-scans the project to extract testable…
erpaval
Workflow for autonomous software development with the Kiro CLI (open Agent Skills standard). Classifiers route scope, complexity, directory state, and spec readiness before committing to Explore / Research / Plan / Act / Validate, then close the loop with a Compound step that persists lessons to .erpaval/solutions/…
idea
Use when exploring a new idea before writing formal specifications. Guides users through iterative discovery, research, and critical analysis to crystallize vague ideas into validated requirement drafts. Includes anti-pseudo-requirement checks, competitive research, demand evidence gathering, and "What if we don't…