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/leadpoet/leadpoet/agents-mdgit clone --depth 1 https://github.com/leadpoet/leadpoetWhat 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 | $0.06205 | $0.06205 |
| Opus 5 | $0.03102 | $0.03102 |
| Sonnet 5 | $0.01241 | $0.01241 |
| Haiku 4.5 | $0.00620 | $0.00620 |
Grade A, and why
leadpoet AGENTS.md scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
fixtures, shell history, or process arguments. Never use `set -x`, `curl -v`, Copies of this mod
1 near-identical copy found in the catalogue:
- leadpoet CLAUDE.md — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 551 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Leadpoet Research Lab agent guide
Applies to this repository unless a deeper AGENTS.md overrides it.
AGENTS.md and CLAUDE.md must remain byte-identical.
Priorities
- Preserve V2 trustlessness and exact-commit behavior.
- Preserve scoring, promotion, rewards, payments, allocation, emissions, and weight submission unless they are explicitly in scope.
- Prefer the smallest correct diff. Do not refactor unrelated code.
- Communicate immediately when scope or expected duration materially grows.
Push-now override
An unambiguous current-turn instruction to push immediately with authorization, including natural-language equivalents of "I authorize you to push now", activates this workflow:
- Fetch and preserve concurrent work, inspect the diff for secrets and unrelated files, then make the smallest correct commit and push within two minutes. Never force-push.
- Run no tests, rehearsal, block check, or attestation check before that first push.
- Immediately run the normal fast gate after the push. Push a follow-up only for a confirmed production-critical defect.
General authorization, "push when ready", or a future conditional instruction does not activate this override.
Repository synchronization
origin/main is authoritative. Open PRs, old worktrees, and copied files are
not.
The canonical local checkout is
/Users/pranav/Downloads/Election_Analysis/Bittensor-subnet. A clean worktree
may be used to protect concurrent work, but synchronizing or pushing from that
worktree does not synchronize the canonical checkout.
Canonical-main parity is a required start and completion gate. Check it before editing, after every fetch or push, and immediately before the final response:
git fetch origin
git status --short --untracked-files=all
git log origin/main..HEAD --oneline
git log HEAD..origin/main --oneline
test "$(git rev-parse HEAD)" = "$(git rev-parse origin/main)"
git diff --exit-code origin/main --
git ls-tree -r --name-only origin/main | while IFS= read -r tracked_path; do
test -e "$tracked_path" || test -L "$tracked_path" || \
printf 'MISSING %s\n' "$tracked_path"
done
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 · 551 lines · 6,205 tokens per session scan A 9315f0ce5c58
leadpoet AGENTS.md is an instructions file published in the GitHub repository leadpoet/leadpoet (11 stars, last pushed 2d ago), licensed MIT. It adds 6,205 tokens to every session, about $0.0310 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
hermes-skilleval AGENTS.md
Instructions for Raidriar7170/hermes-skilleval, a project described as: Verification-gated skill routing and self-improvement harness for Hermes-style agent skills.
open-pencil copilot-instructions.md
Copilot instructions for open-pencil/open-pencil, covering openpencil copilot instructions, pull request requirements, validation and code conventions.
openscreen AGENTS.md
Instructions for getopenscreen/openscreen, covering agents.md, setup commands, development principles, project layout and code style.
openstatus AGENTS.md
AGENTS.md instructions for openstatusHQ/openstatus, covering agents.md, verify your change, toolchain, architecture and tests.
autoharness AGENTS.md
Instructions for tigerless-labs/autoharness: This repo uses Open Knowledge — collaborative markdown via MCP. .open-knowledge/config.yml (with optional /.open-knowledge/config.yml; CLI/env may override) is the path contract: content.dir is the root for relative paths; content.include lists globs that add markdown…
abap2UI5 CLAUDE.md
Instructions for abap2UI5/abap2UI5: All project guidance lives in AGENTS.md — the single source of truth for this repository (architecture and the layered design, the src/00-99 packages, the generated app/webapp mirror, the build and delivery pipeline, the CI gates and ABAP code style).