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 instructions/sodiumsun/agenttrail/agents-mdgit clone --depth 1 https://github.com/sodiumsun/agenttrailWhat 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 | $0.00674 | $0.00674 |
| Opus 5 | $0.00337 | $0.00337 |
| Sonnet 5 | $0.00135 | $0.00135 |
| Haiku 4.5 | $0.00067 | $0.00067 |
Grade A, and why
agenttrail AGENTS.md 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- agenttrail CLAUDE.md — 100% identical, 0 lines differ
What it actually says
agenttrail plan convention
Maintain PLAN.md as the living plan. It is read by the project OWNER, not by you — write it for them.
- nodes are COMPONENTS of the system being built (
## Plain-language name {#id}), not phases or sprints; keep the map at 5-9 components regardless of repo size — grow tasks, not cards, and split a component only when one agent could no longer own it for a session - naming rule: titles are verb-led, plain-language, and CONCRETE — the owner can tell when it is done ("Read alerts out loud", "Watch the repo"). Never engineer-speak ("fs watcher + activity signal") and never vague vibes ("Decide what matters"); put the engineer phrasing on a
tech:line under the heading - tasks inside a component:
- [ ] Plain outcome {#id}, optional indentedtech:line beneath; mark a task[~]BEFORE you start it and save PLAN.md immediately — this drives the live in-progress view; flip it to[x]the moment it completes,[!]if stuck (clear once unblocked). Never batch plan updates for the end of the session - when you mark a task
[~], add an indentedby: <your name>line under it (claude, codex, cursor, …) and leave it there when done — it is the record of who did what - edges under a component heading:
needs: [id, id]= must come after those components;links: [id, id]= interconnected with / talks to files: [src/audio/**, config.py]under a component declares which paths it owns — keep it current; it is how the live view knows which component you are really working in, including when you revisit finished work{#id}s are stable — never rename, only add or remove nodes- open tasks carry an indented
from:line naming their provenance —from: agentwhen YOU are declaring it as your own imminent build intent (the owner corrects these on sight if wrong),from: roadmapwhen it comes from planning documents (durable intent, backloggable); omit when neither - new work NEVER creates a component by default: it lands as your session todos plus tasks under the component whose files it touches. Add a NEW component only when the system grows a durable new part. Durable is not a prediction — test it NOW: something else already depends on it (load-bearing), deleting it would change what the product does, you can name a plausible second task for it, and it owns files no component claims. Record the addition under
## decisions. Time corrects mistakes cheaply: merge a card back into its neighbor if no second change ever comes; promote a task to a card when work keeps clustering in files its siblings never touch. Remove a component only when that part is deleted from the product - before ending a session, graduate your plan-worthy completed todos into PLAN.md as
[x]tasks (withby:) — housekeeping todos stay out of the plan - record any plan-affecting decision under
## decisionsBEFORE implementing it
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 · 16 lines · 674 tokens per session scan A 2b0d80272ccf
agenttrail AGENTS.md is an instructions file published in the GitHub repository sodiumsun/agenttrail (474 stars, last pushed 3d ago), licensed MIT. It adds 674 tokens to every session, about $0.0034 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 instructions, from other repositories
latitude-llm AGENTS.md
AGENTS.md instructions for latitude-dev/latitude-llm, covering agents.md, product scope, repo-wide conventions, how to use this guide and skill glossary.
decant AGENTS.md
Instructions for dosu-ai/decant, covering agents.md, project overview, setup and commands, definition of done and project invariants.
starwind-ui-mcp AGENTS.md
AGENTS.md instructions for starwind-ui/starwind-ui-mcp, covering agent instructions, current documentation, agent skills, issue tracker and triage labels.
crewdesk CLAUDE.md
Instructions for mhmmdglc/crewdesk, covering crewdesk — claude notları, çalıştırma, dizin, bozulmaması gereken kurallar and bilinen açık maddeler.
sprint-mcp CLAUDE.md
Claude Code instructions for cnavta/sprint-mcp, covering claude.md, repository purpose, critical precedence rules, protocol file relationship and sprint protocol overview.
latitude-llm CLAUDE.md
Claude Code instructions for latitude-dev/latitude-llm, a project described as: Latitude is the open-source AI monitoring platform.