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/outfitter-dev/blz/agents-mdgit clone --depth 1 https://github.com/outfitter-dev/blzWhat 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 | $0.01615 | $0.01615 |
| Opus 5 | $0.00807 | $0.00807 |
| Sonnet 5 | $0.00323 | $0.00323 |
| Haiku 4.5 | $0.00161 | $0.00161 |
Grade A, and why
blz 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 yesterday.
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 — 201 lines — stays where its author put it; the contents beside it link to each section on GitHub.
blz Repository Instructions for AI Agents
This file provides comprehensive guidance to AI agents when working with Rust code in this repository.
Important
- Follow the @./.agents/rules/IMPORTANT.md rules
- Check @.agents/logs/ for relevant work logs and session notes
Working Memory
Primary activity log: Linear
- Always locate or create the matching Linear issue before you start work on a branch.
- Capture progress via concise Linear comments whenever you pause, hand off, or finish a slice.
- Keep the issue state current (In Progress, In Review, Done, etc.).
- If a branch is dedicated to an issue, add a summary comment in Linear before switching contexts.
Optional scratch notes (archived)
SCRATCHPAD.mdis archived; prefer Linear for durable history.- Temporary jot notes are fine, but add a dated bullet and migrate/delete them before ending your session.
- Historical scratch snapshots live under
.agents/.archive/logs/.
Use blz
- You're working on blz, so you should use it!
- For docs search, use the
blzCLI tool: @docs/agents/use-blz.md
🚀 Quick Start for Agents
Before You Begin
- Run the agent check script:
./scripts/agent-check.shfor compiler diagnostics and automated fixes - Check current build status:
cargo check --message-format=jsonfor machine-readable errors - Review unsafe code policy: See
.agents/rules/conventions/rust/unsafe-policy.mdif working with unsafe blocks - Prime the build cache:
- Export
RUSTC_WRAPPER=sccachein your shell (or run the bootstrap script) so rebuilds stay fast. - Git worktrees: If using worktrees, setup scripts automatically configure shared
target-shared/to save 40-50% disk space. Check withscripts/prune-shared-target.sh --check. - Single worktree: Run
scripts/prune-target.sh --checkto confirm thetarget/directory isn't bloated; use--prune-debug(and optionally--sweep) when debug caches climb past the threshold.
- Export
Common Agent Pain Points & Solutions
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.
- yesterday First seen · 201 lines · 1,615 tokens per session scan A fcfe2d7b0de2
blz AGENTS.md is an instructions file published in the GitHub repository outfitter-dev/blz (27 stars, last pushed 20d ago), licensed MIT. It adds 1,615 tokens to every session, about $0.0081 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
agent-device AGENTS.md
AGENTS.md instructions for callstack/agent-device, covering agents.md, incident-derived principles, declaration sites and enforcement, hard repository rules and module and test topology.
veritas-kanban AGENTS.md
Instructions for BradGroux/veritas-kanban, covering agents.md — canonical agent instructions for veritas kanban, runtime requirements, repository layout, essential commands and install.
beads AGENTS.md
AGENTS.md instructions for gastownhall/beads, covering agent instructions, key sections, project scope, pr safety for agents and visual design anti-patterns.
ai-agent-board AGENTS.md
Instructions for DanWahlin/ai-agent-board, covering agents.md, project overview, architecture, key technical decisions and running locally.
FlowBoard AGENTS.md
Instructions for rasimme/FlowBoard, covering flowboard — agent entry point, start here and where things live.
lineark CLAUDE.md
Instructions for flipbit03/lineark, covering claude.md — lineark, what is this, workspace layout, key commands and writing online tests: the three pillars.