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/nklisch/skilltap/skilltapnpx skills add nklisch/skilltap --skill skilltapgit clone --depth 1 https://github.com/nklisch/skilltapWhat 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 | $0.00024 | $0.00778 |
| Opus 5 | $0.00012 | $0.00389 |
| Sonnet 5 | $0.00005 | $0.00156 |
| Haiku 4.5 | $0.00002 | $0.00078 |
Grade A, and why
skilltap 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 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.
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 — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Operate the local agent environment
skilltap is a non-interactive control plane for one person's supported local agent harnesses. It manages explicitly selected resources, shared instructions, native marketplaces/plugins, complete skill directories, and drift between desired and observed state. It does not search, rank, browse, or recommend skills, plugins, or marketplaces.
Start with the user's intent
- First-time setup: first check whether
skilltapis available. If it is missing, explain that the plugin does not bundle an executable and use the verified installer fromhttps://skilltap.dev/install.sh(or Homebrew) only with the user's authorization. After the binary exists, runskilltap bootstrap --help, thenskilltap bootstrap. Treat the binary result and each first-party plugin target result as separate facts; Codex may report an unsupported native plugin-install path. - “What is wrong?” or a health check: run
skilltap status --help, thenskilltap status --jsonwhen structured output is useful. - Existing native resources should become managed: use
skilltap adoptafter reviewing status. Adoption observes and records; it does not push changes. - “What would change?”: run
skilltap planand explain its operations, compatibility, ownership, and next actions before mutating anything. - Apply an accepted plan: run
skilltap sync. Useskilltap harness listto inspect target ids,--target <id>to narrow to one harness,--target allto select every enabled harness, and scope flags to choose global or a project. - Explicit marketplace/plugin/skill lifecycle work: use the matching
marketplace,plugin, orskillcommand family. Instructions useinstructions; automatic safe updates use the optionaldaemon.
Always ask the executable for exact syntax at the point of use:
skilltap --help, skilltap <group> --help, and
skilltap <group> <command> --help are authoritative. Do not copy a full flag
table into this skill.
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 68 lines · 24 tokens per session scan A 3b63c61c1eec
skilltap is a skill published in the GitHub repository nklisch/skilltap (6 stars, last pushed 17d ago), licensed MIT. It adds 24 tokens to every session and 778 once invoked, about $0.0001 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 2026-08-31.
Other skills, from other repositories
rust-system-calls
Guides using bunsys for system calls and file I/O in Rust. Use when implementing file operations, opening fds, or any syscall path instead of std::fs or libc.
bunqueue-dev
Internal skill for contributing to bunqueue - architecture, testing, code conventions, and development workflow.
docker-extend
Use when: User wants to extend Docker with custom tools, personalize the Docker environment, or set up user-specific Docker customization. Triggers: 'extend docker', 'docker-extend', 'add tools to docker', 'customize docker', 'add my tools to the container', 'personalize docker setup', 'docker user setup', 'install…
google-meet
Google Meet via gws: create spaces, fetch join links, list recordings.
people-crm
Turn LinkedIn connections (or any contact export) into a queryable personal CRM using the agent database.
clarify-spec
Full execution protocol for MODE: CLARIFY-SPEC -- resolving spec clarification markers and maintaining spec/planning alignment.