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 OutlineDriven/odin-claude-plugin --skill trailmark-summarygit clone --depth 1 https://github.com/OutlineDriven/odin-claude-pluginWrote 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/outlinedriven/odin-claude-plugin/trailmark-summary)<a href="https://agentmods.dev/skills/outlinedriven/odin-claude-plugin/trailmark-summary"><img src="https://agentmods.dev/badge/skills/outlinedriven/odin-claude-plugin/trailmark-summary.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00073 | $0.01076 |
| Opus 5 | $0.00036 | $0.00538 |
| Sonnet 5 | $0.00015 | $0.00215 |
| Haiku 4.5 | $0.00007 | $0.00108 |
Grade A, and why
trailmark-summary 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 4d 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 — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Trailmark summary
Contract
| Field | Bound contract |
|---|---|
| Trigger | The user or another workflow needs a quick structural overview before deeper codebase analysis. |
| Authority | Read-only: no file, VCS, credential, paid, published, deployed, or remote mutation. Never install, upgrade, or clone trailmark or any dependency. |
| Side effect | Reads the target source tree and emits the language list and summary output; writes nothing. |
| Done | Detected languages, Entrypoints, and Dependencies are all present in the returned report, or an installation or language gap is reported. |
Inputs
- Target directory path (required): supplied by the invoker; there is no default. Confirm it exists and is a readable directory before running anything.
Refusals
- Will not install, upgrade, or clone trailmark or any dependency.
- Will not fall back to manual code reading if trailmark is unavailable.
- Will not widen into full structural analysis, hotspot scores, or taint data.
- Will not fabricate output or claim Done while a field is missing without naming the gap.
Procedure
- Validate the target at its trust boundary: confirm the supplied path exists and is a directory. If not, report the invalid target and stop. Done when: the target is confirmed as a readable directory.
- Check that trailmark is available:
trailmark analyze --help 2>/dev/null || uv run trailmark analyze --help 2>/dev/null. If neither command works, reporttrailmark is not installedand stop. Never runpip install,uv pip install,git clone, or any install command. Done when: trailmark availability is confirmed or the installation gap is reported. - Optionally record the version if the installed build supports it:
trailmark --version 2>/dev/null || uv run trailmark --version 2>/dev/null || true. Do not fail if the version command is missing; this is the v0.2-safe summary workflow and does not require Trailmark 0.4.0 or newer. Done when: the version is recorded or confirmed absent. - Detect languages with Trailmark's parse API. If the import fails, rerun the same snippet with
uv run --with trailmark python - "<target-directory>". If the result is[], reportTrailmark found no supported languages under targetand stop. Done when: the detected language list is returned or the language gap is reported. - Run the summary with auto-detection:
trailmark analyze --language auto --summary <target-directory> 2>&1 || uv run trailmark analyze --language auto --summary <target-directory> 2>&1. Run only this summary pass; do not widen into full structural analysis, hotspot scores, or taint data. Done when: the summary output is captured. - Verify the output includes all three of: the detected languages from step 4, an
Entrypoints:line, and aDependencies:line. If any are missing, report exactly which field is missing and stop. Do not fabricate output. Done when: all three fields are present. - Return the detected language list plus the full Trailmark summary output. If a version string was captured in step 3, include it in the returned metadata. Done when: the report is returned.
What ships with it
1 file 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.
- 4d ago First seen · 53 lines · 73 tokens per session scan A 7b7ebbb1e26b
trailmark-summary is a skill published in the GitHub repository OutlineDriven/odin-claude-plugin (35 stars, last pushed yesterday), licensed Apache-2.0. It adds 73 tokens to every session and 1,076 once invoked, about $0.0004 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 2026-09-04.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…