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/arpitkath/backstory/claude-mdgit clone --depth 1 https://github.com/arpitkath/backstoryWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/instructions/arpitkath/backstory/claude-md)<a href="https://agentmods.dev/instructions/arpitkath/backstory/claude-md"><img src="https://agentmods.dev/badge/instructions/arpitkath/backstory/claude-md.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00723 | $0.00723 |
| Opus 5 | $0.00362 | $0.00362 |
| Sonnet 5 | $0.00145 | $0.00145 |
| Haiku 4.5 | $0.00072 | $0.00072 |
Grade A, and why
backstory CLAUDE.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 6d 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 — 104 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
Repository instructions for Claude-based work in this repo.
Project Summary
Backstory is a local-first AI memory layer for Git repositories. It stores
session history as OKF markdown under .backstory/knowledge/ and links that
memory to commits. Capture should come from tool-native hooks, callbacks, or
transcript exporters, not from Git hooks.
Current State
- Session persistence uses OKF markdown, not JSON.
- Pending sessions live at
.backstory/knowledge/sessions/latest.md. - Attached sessions live as stable
.mdfiles in the same directory. backstory diffcan warn about likely contradictions with previous sessions.backstory dumpis the ingestion step used by tool integrations.
Development (source-only)
Run the CLI directly from the source tree — no pip install needed.
# Run the backstory CLI from local source
python -m backstory <command>
# Run tests
PYTHONPATH=src python -m pytest -q
Important Commands
Useful CLI commands (requires installation or python -m backstory):
backstory init
backstory attach HEAD
backstory why HEAD
backstory file <path>
backstory line <path>:<line>
backstory range <path>:<start>-<end>
backstory code <path>:<start>-<end>
backstory diff
backstory status
Publishing (via GitHub Actions)
The package is published to PyPI as backstory-cli via GitHub Actions.
How to publish
- Bump version in
pyproject.toml(semver: bugfix → patch, new feature → minor, breaking → major) - Commit and push the version bump
- Create a GitHub Release from the pushed tag — the
publish.ymlworkflow auto-deploys
Workflow
- Trigger:
on: release: [published] - Uses trusted publishing (OIDC) — no tokens to manage
- Dry-run:
gh workflow run publish.yml -f dry_run=true
Manual publish (fallback)
If CI is down, publish from local:
pip install build twine
python -m build
twine upload dist/backstory_cli-*
Requires a PyPI API token from https://pypi.org/manage/account/token.
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.
- 6d ago First seen · 104 lines · 723 tokens per session scan A 8b6b567e3f2c
backstory CLAUDE.md is an instructions file published in the GitHub repository arpitkath/backstory (10 stars, last pushed 1mo ago), licensed MIT. It adds 723 tokens to every session, about $0.0036 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
remnic AGENTS.md
AGENTS.md instructions for joshuaswarren/remnic, covering remnic - agent guide, architecture boundaries (non-negotiable), upstream references, adapter implementation rules and openclaw compatibility window.
plur CLAUDE.md
Claude Code instructions for plur-ai/plur, covering claude.md, what is plur, development, package dependency and version bumps.
engraphis AGENTS.md
AGENTS.md instructions for Coding-Dev-Tools/engraphis, covering agents.md — engraphis, internal subagent delegation, 0. read this first — two architectures live in one package, 1. commands and ── unified dashboard + memory inspector ──.
Agent-Memory-Bridge AGENTS.md
Instructions for zzhang82/Agent-Memory-Bridge, covering agent memory bridge contributor instructions, setup and checks, architecture boundaries, mutation and migration invariants and benchmark expectations.
brain-os AGENTS.md
Instructions for brainOS-HQ/brain-os, covering agents.md, context, the hard rule, tool routing (in order) and mutation safety.
hunch copilot-instructions.md
Copilot instructions for davesheffer/hunch, covering copilot instructions, 🧠 hunch (engineering memory) and ⛔ top invariants (do not break).