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 bearded-illirian/trailmark --skill library-firstgit clone --depth 1 https://github.com/bearded-illirian/trailmarkWrote 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/bearded-illirian/trailmark/library-first)<a href="https://agentmods.dev/skills/bearded-illirian/trailmark/library-first"><img src="https://agentmods.dev/badge/skills/bearded-illirian/trailmark/library-first/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/bearded-illirian/trailmark/library-first"><img src="https://agentmods.dev/badge/skills/bearded-illirian/trailmark/library-first.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00077 | $0.01736 |
| Opus 5.5 | $0.00031 | $0.00694 |
| Sonnet 5.5 | $0.00015 | $0.00347 |
| Haiku 4.5 | $0.00008 | $0.00174 |
Grade A, and why
library-first 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 — 203 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Library-First Protocol
Runs first in a fast-track task. Does nothing until explicit user approval.
Input
The approved flow-first-{N}.{R}.md with Landscape and Solution cells identifying what exists vs what needs building.
Output
A LOC table with 5 columns (What we do / Source / What we use / LOC / Type) plus Watchpoints and Out-of-scope blocks, saved as library-first-{N}.{R}.md.
Hands off to
plan-first (auto-invoked after user approval).
Step 0 — Check task context
Check: are {log_dir} and {slug} known in the current session?
If yes — continue. If no — list the latest task folders under {tasks_root}/log/ and ask which is current, then set {slug} and {log_dir}. Cannot skip — without {log_dir} the artifact won't be saved.
Step 0.5 — Chain verification
If {N} is known — check for a flow-first artifact:
ls "{log_dir}"/flow-first-{N}.*.md 2>/dev/null | head -1
File found → continue. Not found → invoke Skill(flow-first) and resume after it completes. {N} unknown → silently skip.
Step 0.5.1 — Read and extract Solution
From the flow-first file extract: Landscape / Problem / Solution / Result across three axes (UI / DB / Integrations).
Use Solution as the basis for atoms in Step 1. Use Landscape for the "Source" field: existing component mentioned → Library ✅; not mentioned → From scratch ⚠️.
If the flow-first table is empty or all cells say "not involved" — prompt once to repeat flow-first; on retry, continue with what's there.
Step 1 — Task analysis
Break the task into atomic parts. For each part determine:
- Source: existing component/library →
Library ✅; nothing suitable →From scratch ⚠️ - What we use: specific file/component name. If from scratch — "no ready-made"
- LOC: approximate new lines. Library — 0 or minimum for integration
Step 2 — Output the table
| # | What we do | Source | What we use | LOC | Type |
|---|-------------------|-----------------|-----------------|-----|----------|
| 1 | [action] | Library ✅ | [file] | 0 | ui |
| 2 | [action] | From scratch ⚠️ | no ready-made | ~40 | ai-skill |
Total new lines of code: ~40
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.
- 1mo ago Changed a95f682b2055
- 1mo ago First seen · 203 lines · 77 tokens per session scan A 0c22b17381fd
library-first is a skill published in the GitHub repository bearded-illirian/trailmark (19 stars, last pushed 1mo ago), licensed MIT. It adds 77 tokens to every session and 1,736 once invoked, about $0.0003 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
stub_distance_skill
a deterministic stub returned by the override engine in unit tests.
generated_skill_1775724185480
Parse XBRL financial documents and extract key taxonomy elements into structured JSON format.
paperclip
Use for Paperclip-managed tasks and heartbeats: reading task context, delivering task documents or files, updating completion or blockers, coordinating or delegating work, and following company governance. Includes control plane API operations for assignments, comments, approvals, and routines.
agentmail
Use your assigned AgentMail inbox to read email tasks, explicitly send or reply, and check delivery. Provided automatically by your inbox assignment.
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
interview
Ask one useful structured question at a time only when material product/implementation choices are genuinely missing; remember answers and produce a brief/spec. Discoverable facts should be investigated instead of asked.