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/bearded-illirian/trailmark/plan-firstnpx skills add bearded-illirian/trailmark --skill plan-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/plan-first)<a href="https://agentmods.dev/skills/bearded-illirian/trailmark/plan-first"><img src="https://agentmods.dev/badge/skills/bearded-illirian/trailmark/plan-first.svg" alt="Measured on agentmods" 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 | $0.00075 | $0.01275 |
| Opus 5 | $0.00037 | $0.00638 |
| Sonnet 5 | $0.00015 | $0.00255 |
| Haiku 4.5 | $0.00007 | $0.00128 |
Grade A, and why
plan-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 5d 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 — 175 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Plan-First Protocol
Mandatory protocol before any of the following:
- Writing a document (spec, README, guide, architecture)
- Writing new code (file, module, component)
- Refactoring existing code
- Database migration
- Writing tests / test plan
- Git operations (commit, PR, merge)
Input
The approved library-first-{N}.{R}.md with atomic rows the plan will execute.
Output
A 7-15 row plan table saved as plan-first-{N}.{R}.md; after execution — report-{N}.{R}.md and user-note-{N}.{R}.md.
Hands off to
ship-first — per-block mode closes the block and moves to next; task-level mode closes the task.
Step 0 — Task context
Ensure {log_dir} and {slug} are known.
Step 1 — Build the plan table
A table of 7–15 rows. Each row = one atomic step.
Columns:
- # — sequential number
- Step title — verb + object ("create X", "update Y", "delete Z")
- Short summary — 1 sentence what this step actually does
Rules:
- 7 to 15 rows — fewer means the block is too small (skip planning), more means it's too big (decompose)
- Right column is a concrete summary, not "TBD" or empty
- No research steps ("read X", "figure out Y") — those belong in flow-first / library-first, not plan-first
Step 2 — Show table + pick mode
Show the plan table to the user. Ask for one of three modes:
Mode:
1 — Autopilot: I execute every step without pauses, then a final report
2 — Step-by-step: I pause after each step, wait for "ok" to continue
3 — Draft only: I don't execute, just save the plan for later
Wait for the user's response.
Auto-execution context (e.g. dev-auto-first): mode = 1 (autopilot) chosen automatically.
Step 3 — Save the artifact
Write {log_dir}/plan-first-{N}.{R}.md where:
N= current block numberR= round (1 by default, 2+ on revision)
Structure:
> 🔗 Task: tasks/log/{slug}/task.md
# plan-first — plan for block {N}
**Date:** {date}
**Mode:** {chosen mode}
## Plan
| # | Step title | Short summary |
|:-:|---|---|
| 1 | ... | ... |
| ... | ... | ... |
## Risks
- {risk 1}
- ...
## Out of scope
- {what is deliberately not done in this block}
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.
- 5d ago First seen · 175 lines · 75 tokens per session scan A 1870576fa763
plan-first is a skill published in the GitHub repository bearded-illirian/trailmark (19 stars, last pushed 3d ago), licensed MIT. It adds 75 tokens to every session and 1,275 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 2026-08-30.
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.
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.
local-frontend-check
Smoke-test or verify UI behaviour on the local Jarvis Registry frontend running at http://localhost/gateway. Use for manual regression checks, bug-fix verification, and end-to-end confirmation of specific flows without running the automated test suite.
ppt-review
Read this skill only after current officereview structural output and relevant rendered images exist. Do not use source code, a tool success flag, or the first-slide preview as a substitute for deck evidence.