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/aspenkit/aspens/template-librarynpx skills add aspenkit/aspens --skill template-librarygit clone --depth 1 https://github.com/aspenkit/aspensWhat 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 | $0.00043 | $0.01286 |
| Opus 5 | $0.00022 | $0.00643 |
| Sonnet 5 | $0.00009 | $0.00257 |
| Haiku 4.5 | $0.00004 | $0.00129 |
Grade A, and why
template-library 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 yesterday.
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 — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are working on the template library — bundled agents, slash commands, hooks, and settings that users browse and install into their repos.
Domain purpose
aspens add <type> [name] copies curated templates into a consumer repo's .claude/ directories so users get working agents, slash commands, hooks, and settings without authoring them. The same template tree is reused by aspens doc init (hook installation, recommended agents) and aspens save-tokens (handoff tooling). Custom skills can also be scaffolded blank or LLM-generated from a reference doc.
Key Concepts
- Four resource types for
add:agent→.claude/agents,command→.claude/commands,hook→.claude/hooks. A fourth typeskillis handled separately (not template-based). - Save-tokens templates:
save-tokens.mjsis the runtime entry point for all three hook entry points (statusline, prompt-guard, precompact). Shell wrappers (save-tokens-*.sh) resolve project dir and delegate to the.mjsfile. Slash commands (save-handoff.md,resume-handoff.md,resume-handoff-latest.md) provide user-invokable handoff management. These are installed byaspens save-tokensoraspens doc init --recommended, not byaspens add. - Codex-only restriction:
add agent,add command, andadd hookthrowCliErrorfor Codex-only repos. Skills work with both targets. - Target-aware skill commands:
addSkillCommandandgenerateSkillFromDocresolve the active target viaresolveSkillTarget(config). Skill paths usetarget.skillsDirandtarget.skillFilename. - Backend-aware generation:
generateSkillFromDocusesrunLLM()to dispatch to Claude or Codex based on config. - Hook templates (monorepo-aware): Shell hooks compute
PROJECT_DIRfrom the script's own location (cd "$SCRIPT_DIR/../.." && pwd) and pass it asASPENS_PROJECT_DIRto.mjscounterparts. Save-tokens shell hooks follow the same pattern. - Settings template quoting: Hook commands in
settings.jsonare wrapped in double quotes for shell safety. doc inithook installation (step 13): Generatesskill-rules.json, copies hook files, generatespost-tool-use-tracker.shwith domain patterns, mergessettings.jsonwith backup.doc init --recommendedextras (step 15): Copies all bundled agent templates to.claude/agents/(skips existing), addsdev/to.gitignore.- Template discovery:
listAvailable()reads template dir, filters.md/.shfiles, regex-parsesname:anddescription:. - No-overwrite policy:
addResource()skips files that already exist. Same foraddSkillCommand. - Plan/execute gitignore: Adding
planorexecuteagents auto-addsdev/to.gitignorefor plan storage.doc init --recommendedalso ensuresdev/in.gitignore. - Base-skill warning for agents:
addResource()prints a non-fatal yellow warning when installing an agent if.agents/skills/base/SKILL.mdis missing, prompting the user to runaspens doc init. The agent still installs.
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.
- yesterday First seen · 59 lines · 43 tokens per session scan A 668cbffb8a00
template-library is a skill published in the GitHub repository aspenkit/aspens (96 stars, last pushed 16d ago), licensed MIT. It adds 43 tokens to every session and 1,286 once invoked, about $0.0002 per session on Opus 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
golden-rss
Use when testing the rss golden build.
golden-chat-topics
Use when testing the goldenchattopics golden build.
golden-chat-single
Use when testing the goldenchatsingle golden build.
decided-import
Reformat ONE existing document (a decision, requirement, design, roadmap, or prompt) into ONE valid RAC (requirements-as-code) artifact, with a mandatory human-review step before any file is written and decided validate as the deterministic close. Use when a user wants to add or import a single existing decision or…
keep-the-why
Preserves or recovers the reasoning behind a codebase - architectural decisions, rejected alternatives, workarounds, incident learnings, operational constraints, and historical context the code itself cannot explain. Use when implementing or reviewing a non-trivial change involving a design decision, workaround…
summarize
Summarize conversations, logs, docs, or investigation notes into action-oriented text with evidence tags. Use for recap, handoff, CI failure digest, or MEMORY. Triggers: 总结, 汇总, summarize, 交接, 复盘, 调试总结.