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 1amageek/swift-skeleton --skill skeletongit clone --depth 1 https://github.com/1amageek/swift-skeletonWrote 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/1amageek/swift-skeleton/skeleton)<a href="https://agentmods.dev/skills/1amageek/swift-skeleton/skeleton"><img src="https://agentmods.dev/badge/skills/1amageek/swift-skeleton/skeleton/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/1amageek/swift-skeleton/skeleton"><img src="https://agentmods.dev/badge/skills/1amageek/swift-skeleton/skeleton.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00115 | $0.01755 |
| Opus 5.5 | $0.00046 | $0.00702 |
| Sonnet 5.5 | $0.00023 | $0.00351 |
| Haiku 4.5 | $0.00012 | $0.00176 |
Grade A, and why
skeleton 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 — 137 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skeleton
Use skltn to locate the source that requires inspection without loading implementation bodies. Treat its output as a structural index, never as implementation truth.
Workflow
1. Resolve the project root
Use the path supplied by the user. If no path is supplied, use the current working directory.
2. Build a structural map
skltn get [project-root] [options]
Choose the narrowest view that preserves the context required by the task:
- When a SwiftPM target or module is known, use
--targetby default. This keeps the focus target complete and adds only the source-visible surface of direct imported local dependencies. - For a large target, begin with
--headers-only, then rerun without it only when member signatures are required. - When the user requests an exact file or directory boundary, use that path without target expansion.
- When no target is known, begin with a repository-wide
--headers-onlymap, identify the relevant target, then switch to target mode.
skltn get <package-root> --target <target-name> --headers-only
skltn get <package-root> --target <target-name>
Use --path <relative-file> for one indexed file, --language <name> to restrict parsers, and --kind <kind> to restrict supported declaration kinds.
Keep path and target intent distinct:
skltn get Sources/Feature
skltn get Sources --target Feature
The first command strictly scans Sources/Feature. The second resolves the SwiftPM target, renders it in full, and adds only source-visible declarations from direct local dependencies that the target imports. Use --access public only when the task needs the externally consumable API surface rather than the target's full implementation-facing structure.
The get command may be omitted. skeleton, get_skeleton, and build are compatibility aliases.
3. Verify the selected source
Use the skeleton map to choose files and ranges, then read the original code before making an implementation claim or change. For each relevant path:
What ships with it
2 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.
- 1mo ago First seen · 137 lines · 115 tokens per session scan A 9e59ac1f4392
skeleton is a skill published in the GitHub repository 1amageek/swift-skeleton (17 stars, last pushed 19d ago), licensed MIT. It adds 115 tokens to every session and 1,755 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
remarc
Manage Remarc session comments and contextual feedback. Use when the user mentions Remarc sessions, comments, handoff, triage, review, addressing, resolving, status updates, or summaries.
code-review
Review code for quality, maintainability, and correctness.
sem
Use sem for entity-level (function/class/method) code questions in any Git repo. Four questions, four verbs - where is it (sem find, sem grep), what does my change touch (sem impact), is it correct (sem check), what should a human review (sem certify). Trigger whenever the user asks where something is defined or…
sem-code-review
Find named code entities, inspect callers, and review changed functions with the locally installed Ataraxy Sem CLI. Use for code discovery or Git change review when Sem is available.
release-pr-review
Review pass on an open release PR (release/ → main) — the step between git-wrapup and release-and-publish when a project releases in gated release PR mode. Reads the PR's commit range through the code-simplifier lens plus a correctness review, verifies whatever an automated reviewer left on the PR, lands fixes as…
github-commenting
How to post clean, rich, deduplicated GitHub PR review comments — suggestion blocks, multi-line anchors, markers, formatting rules. Load before posting or fixing any PR comment.