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/mrlesk/backlog.md/agents-mdgit clone --depth 1 https://github.com/MrLesk/Backlog.mdWhat 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 | $0.01637 | $0.01637 |
| Opus 5 | $0.00818 | $0.00818 |
| Sonnet 5 | $0.00327 | $0.00327 |
| Haiku 4.5 | $0.00164 | $0.00164 |
Grade A, and why
Backlog.md 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 today.
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 — 126 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Read This First
At the beginning of each conversation, read MANIFESTO.md in the repository root before doing anything else. It is the project's constitution: who Backlog.md serves, its core loop, source of truth, surface hierarchy, interface posture, design principles, boundaries, and risks. All architecture and product decisions must align with it.
If a request appears to conflict with the manifesto, or would materially change a principle in it, surface the conflict and ask Alex rather than silently proceeding. Do not edit the manifesto as a side effect of implementation; changes to it require an explicit product decision.
When you're working on a task, you should assign it yourself: -a @{your-name}
In addition to the rules above, please consider the following: At the end of every task implementation, try to take a moment to see if you can simplify it. When you are done implementing, you know much more about a task than when you started. At this point you can better judge retrospectively what can be the simplest architecture to solve the problem. If you can simplify the code, do it.
Simplicity-first implementation rules
- Prefer a single implementation for similar concerns. Reuse or refactor to a shared helper instead of duplicating.
- Keep APIs minimal. Favor load + upsert over load/save/update, and do not add unused methods.
- Avoid extra layers (services, normalizers, versioning) unless there is an immediate, proven need.
- Keep behavior consistent across similar stores (defaults, parse errors, locking). Divergence requires a clear reason.
- Don't add new exported helpers just to compute a path; derive from existing paths or add one shared helper only when reused.
UI descriptions
Do not add subtitles, helper text, or descriptive copy beneath headings, labels, cards, or settings by default. Prefer one concise, self-explanatory heading or label. Only add supporting copy when the user explicitly asks for it or when it is necessary to prevent misunderstanding or error, and never use it to restate the heading.
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.
- today Changed · +18 tokens per session e85e312384c4
- 3d ago First seen · 126 lines · 1,619 tokens per session scan A fe4e19cd5ce3
Backlog.md AGENTS.md is an instructions file published in the GitHub repository MrLesk/Backlog.md (6,602 stars, last pushed yesterday), licensed MIT. It adds 1,637 tokens to every session, about $0.0082 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
vibe-kanban AGENTS.md
Instructions for BloopAI/vibe-kanban, covering repository guidelines, project structure & module organization, crate-specific guides, managing shared types between rust and typescript and build, test, and development commands.
vibe-kanban CLAUDE.md
Instructions for BloopAI/vibe-kanban, a project described as: Get 10X more out of Claude Code, Codex or any coding agent.
mini-swe-agent copilot-instructions.md
Copilot instructions for SWE-agent/mini-swe-agent, covering style guide, test style, bad and good.
ii-agent AGENTS.md
Instructions for Intelligent-Internet/ii-agent, covering ii-agent contributor guide, quick start, repository map, mandatory rules and architecture.
intelligent-terminal rust.instructions.md
Concise Rust coding conventions for this repository.
agentrq AGENTS.md
Instructions for agentrq/agentrq, covering agentrq codebase notes, project layout, running tests, mcp server (backend/internal/controller/mcp/) and events (experimental).