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/machinewisdomai/fava-trails/agents-mdgit clone --depth 1 https://github.com/MachineWisdomAI/fava-trailsWrote 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/instructions/machinewisdomai/fava-trails/agents-md)<a href="https://agentmods.dev/instructions/machinewisdomai/fava-trails/agents-md"><img src="https://agentmods.dev/badge/instructions/machinewisdomai/fava-trails/agents-md.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 | $0.03616 | $0.03616 |
| Opus 5 | $0.01808 | $0.01808 |
| Sonnet 5 | $0.00723 | $0.00723 |
| Haiku 4.5 | $0.00362 | $0.00362 |
Grade A, and why
fava-trails 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 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 — 326 lines — stays where its author put it; the contents beside it link to each section on GitHub.
FAVA Trails — Agent Reference 🫛👣
Agent-facing reference for FAVA Trails MCP tools. For project setup and configuration, see README.md. For the full session protocol with examples, see AGENTS_USAGE_INSTRUCTIONS.md.
Repository Workflow
- Development:
~/git/MachineWisdomAI/fava-trails/(this repo) - Never modify:
~/git/vendor/fava-trails/(read-only, pinned for running MCP servers) - Feature branches use worktrees:
~/git/MachineWisdomAI/fava-trails-{slug}/ - Never commit directly to
main— always use a feature branch and PR - Pre-flight before starting work:
git worktree list && git branch -r - If another agent or branch is active on this repo, coordinate or use a separate worktree.
Scope Discovery
Every tool call requires trail_name — a slash-separated scope path (e.g. mw/eng/fava-trails). Resolve in priority order:
| Priority | Source | Set where |
|---|---|---|
| 1 | FAVA_TRAILS_SCOPE env var |
.env (gitignored) — per-worktree override |
| 2 | .fava-trails.yaml scope |
Project root (committed) — default for all clones |
| 3 | FAVA_TRAILS_SCOPE_HINT |
MCP server env block — broad fallback |
If FAVA_TRAILS_SCOPE is not set but .fava-trails.yaml exists, read the scope field and write it to .env as FAVA_TRAILS_SCOPE=<scope>. If neither exists, use the scope hint from tool descriptions and prompt the user to create a .fava-trails.yaml.
See AGENTS_USAGE_INSTRUCTIONS.md for full scope discovery protocol with examples.
Session Start Protocol
Before starting work, recall existing context:
recall(trail_name="<scope>", query="status")
recall(trail_name="<scope>", query="decisions")
recall(trail_name="<scope>", query="gotcha", scope={"tags": ["gotcha"]})
Use trail_names with globs for broader context: recall(trail_name="<scope>", query="architecture", trail_names=["mw/eng/*"])
Scope Lookup Discipline
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 · 326 lines · 3,616 tokens per session scan A 7e7e7a877d9b
fava-trails AGENTS.md is an instructions file published in the GitHub repository MachineWisdomAI/fava-trails (25 stars, last pushed today), licensed Apache-2.0. It adds 3,616 tokens to every session, about $0.0181 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
summonpot AGENTS.md
AGENTS.md instructions for tugrulguner/summonpot, covering agents.md, what summonpot is, layout, coding guidelines and workflow.
deepagents AGENTS.md
AGENTS.md instructions for langchain-ai/deepagents, covering global development guidelines for the deep agents monorepo, corridor security analysis, development workflow, suppressing ruff rules and pr conventions.
mini-swe-agent copilot-instructions.md
Copilot instructions for SWE-agent/mini-swe-agent, covering style guide, test style, bad and good.
Embody AGENTS.md
AGENTS.md instructions for dylanroscover/Embody, covering embody + envoy - ai instructions, critical rules, td python rules, network layout rules and mcp server safety rules.
intervals-icu-mcp CLAUDE.md
Claude Code instructions for hhopke/intervals-icu-mcp, covering claude.md, project overview, development commands, architecture (quick reference) and tool categories.
valuecell AGENTS.md
Instructions for ValueCell-ai/valuecell, covering guidelines, python programming, python environment, imports and runtime checks.