backpass AGENTS.md

Project memory instructions for backpass, an npm command-line tool that reviews earlier agent sessions and proposes evidence-based updates to AGENTS.md or CLAUDE.md files.

In plain words
What is it for?
They are for orienting agents in the repository, tracing the analysis pipeline, and maintaining project instructions based on past work.
Why use it?
They help coding agents understand the project’s governing documents, processing stages, and rules before changing the tool.

Instructions file for CodexOpenCode

Install

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.

agentmods
npx agentmods add instructions/kunchenguid/backpass/agents-md
Clone the repo
git clone --depth 1 https://github.com/kunchenguid/backpass

Made for: Codex, OpenCode.

Per session 5,264 This file is loaded in full into every session.
When invoked 5,264 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.05264 $0.05264
Opus 5 $0.02632 $0.02632
Sonnet 5 $0.01053 $0.01053
Haiku 4.5 $0.00526 $0.00526

Measured 2d ago against content hash 1d39066700fa, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

backpass 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.

AGENTS.md · 272 lines

How it starts

The opening of the file, as written. The whole thing — 272 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Project agent memory

backpass is an npm CLI that runs a "backward pass" over a repo's agent memory files: it discovers past agent-session transcripts tied to the repo, analyzes them, and proposes evidence-backed edits to AGENTS.md / CLAUDE.md under a token budget.

Orientation

  • VISION.md is the acceptance policy: what a change must be true to, and its closing accept/resist tests. VISION-ANSWERS.md records the hypotheticals the author ruled on and why, so a change that argues one of those calls should go the other way starts there.
  • README.md documents the user-facing surface; src/cli.js is the authoritative flag list.
  • The pipeline is one stage per module, in order: src/discovery/ -> src/sample.js (cap) -> src/distill.js -> src/analyze.js -> src/consolidate.js (gap-identity merge, inside foldForRun) -> src/fold.js -> src/synthesize.js (with src/workspace.js + src/diff.js) -> src/proposal.js -> src/apply/. Each module's header comment explains its role; read those before changing a stage.
  • User-facing step names are the training-loop terms, not the module names: discover = "collect samples", analyze = "calculate loss", fold = "aggregate gradients", synthesize = "gradient descent" (STAGE_LABELS in src/tui/render.js). Internal keys, event names, and the typed subcommands (scan, analyze, propose) keep their short names; only what the user reads changes. Never introduce a multi-word subcommand.
  • Zero runtime dependencies, ESM, no build step. Node >= 22.5 (for node:sqlite).
  • pnpm is the package manager; pnpm run check runs lint, format:check, typecheck, and tests. All tests are offline and use fixtures under test/fixtures/. Supply-chain settings (release-age cooldown, build-script deny) live in pnpm-workspace.yaml.
  • Releases are automated by release-please (.github/workflows/release-please.yml, npm trusted publishing). Never hand-edit CHANGELOG.md or .release-please-manifest.json; CI guards reject PRs that touch them.
  • .github/workflows/no-mistakes-required.yml is a thin caller of the shared kunchenguid/no-mistakes/.github/actions/require-no-mistakes composite action, pinned to an immutable commit SHA and never @main. Enforcement logic and tests live upstream in the no-mistakes repository; change enforcement there, never by copying it locally, and bump the pin in a deliberate separate PR. This repo still owns the on:, concurrency, permissions, job name, and author-exemption if:. The action binds the attestation to the head SHA, so a PR whose body no-mistakes did not rewrite for the current head goes red by contract: push through git push no-mistakes.

Read the full file on GitHub · 272 lines

Changes

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.

  1. 2d ago First seen · 272 lines · 5,264 tokens per session scan A 1d39066700fa

Subscribe to this mod's changes

backpass AGENTS.md is an instructions file published in the GitHub repository kunchenguid/backpass (600 stars, last pushed 2d ago), licensed MIT. It adds 5,264 tokens to every session, about $0.0263 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.

Related

Other instructions, from other repositories

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.

openai/codex · 5,182 tokens

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).

microsoft/vscode · 6,785 tokens

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.

vercel/next.js · 7,296 tokens

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).

microsoft/vscode · 5,001 tokens

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.

github/spec-kit · 7,104 tokens

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.

langchain-ai/langchain · 4,345 tokens