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/thedoublejay/gather-step/agents-mdgit clone --depth 1 https://github.com/thedoublejay/gather-stepWhat 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 | $0.00905 | $0.00905 |
| Opus 5 | $0.00452 | $0.00452 |
| Sonnet 5 | $0.00181 | $0.00181 |
| Haiku 4.5 | $0.00090 | $0.00090 |
Grade A, and why
gather-step 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.
How it starts
The opening of the file, as written. The whole thing — 45 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — Gather Step
Memory file for Codex / Gather Step agents. Project conventions and the canonical workflows for this codebase.
Conventions
- Commit messages: Conventional Commits (
feat:,fix:,docs:,refactor:,test:,chore:, etc.). Keep the subject under 72 characters. - No trailers: Never add
Co-Authored-ByorSigned-off-byto commits. - Signing: Tests must run cleanly with
commit.gpgsign = trueset globally. Fixture helpers that create git commits must disable signing locally (e.g.,git -c commit.gpgsign=false commit ...) so CI and dev environments that have GPG signing enabled do not break. - Lint bar:
cargo clippy --workspace --all-targets -- -D warningsmust pass clean. No#[allow(clippy::...)]without an#[expect(..., reason = "...")]that explains why. - Formatting:
cargo fmt --allbefore committing.rustfmt.tomlis the authority. - Type-check first: Run
cargo check --workspacebefore submitting any change that touches non-trivial Rust.
Reviewing a PR with gather-step
When the user says "review this PR using gather-step" (or any close variant — "review the PR", "do a structural review with gather-step", etc.):
- Run
gather-step pr-review --base <base> --head <head> --jsonto build the review index and emit a structured delta report. Use--keep-cacheif the user wants to ask follow-up questions against the review index. - Warn the user before the first run that it will take a minute or two: a fresh review index is being built from scratch in a disposable Gather Step storage. Subsequent runs against the same SHAs may reuse the cache.
- Read the report's
metadata,safety,changed_files, andsuggested_followups. The currentschema_version(defined byDELTA_REPORT_SCHEMA_VERSIONincrates/gather-step-cli/src/pr_review/delta_report.rs) populatesroutes,symbols,payload_contracts,events,decorators,contract_alignments,removed_surface_risks, anddeploymentin addition to the metadata surfaces — none of these are stubs. - For deep follow-ups, run the suggested commands as-is. They include
--registry/--storageoverrides pointing at the kept review index, so they read the PR-branch state, not the workspace baseline. - Only fall back to manual diff inspection if
pr-reviewis unavailable or fails. Never silently skip it for a structured review request.
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 · 45 lines · 905 tokens per session scan A 80f06824363d
gather-step AGENTS.md is an instructions file published in the GitHub repository thedoublejay/gather-step (9 stars, last pushed 27d ago), licensed MIT. It adds 905 tokens to every session, about $0.0045 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 2026-08-31.
Other instructions, from other repositories
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.