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/dosatos/minimise/claude-mdgit clone --depth 1 https://github.com/dosatos/minimiseWrote 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/dosatos/minimise/claude-md)<a href="https://agentmods.dev/instructions/dosatos/minimise/claude-md"><img src="https://agentmods.dev/badge/instructions/dosatos/minimise/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 | $0.01156 | $0.01156 |
| Opus 5 | $0.00578 | $0.00578 |
| Sonnet 5 | $0.00231 | $0.00231 |
| Haiku 4.5 | $0.00116 | $0.00116 |
Grade A, and why
minimise 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 5d 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 — 117 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Claude Code Project Settings
Quick Start
Global commands (work everywhere):
/onboard # Read latest handoff + get oriented
/handoff # Create session handoff for next time
Or manually:
cat worklogs/handoffs/session-latest.md
Scratch & Generated Files — Keep the Repo Root Clean
NEVER write scratch, test, or generated artifacts to the repo root. They pollute
the package. Put them under worklogs/ (gitignored) instead:
- Throwaway plan YAMLs, sample plans, experiment configs →
worklogs/scratch/ - Test-run output / captured logs →
worklogs/(or pipe to/tmp) - Session handoffs →
worklogs/handoffs/ - Working plan docs →
docs/plans/*.md(gitignored; onlydocs/plans/completed/is tracked) - Agent/tool working dirs are local-only and globally ignored
The root must stay limited to real package files (src/, tests/, docs/,
packaging, README). If a tool needs a path, point it at worklogs/.
Environment
- Python: 3.9+
- Package: minimise (pip install -e .)
- Entry Point:
minicommand - Tests:
pytest tests/ -v(42/42 passing) - Config:
~/.minimise/(auto-created)
Session Handoff
At end of each session:
cp worklogs/handoffs/HANDOFF_TEMPLATE.md worklogs/handoffs/session-YYYY-MM-DD-HHmm.md
# Fill in: what was done, what's next, how to run, gotchas, current state
ln -sf session-YYYY-MM-DD-HHmm.md worklogs/handoffs/session-latest.md
Next session, read the handoff to get context.
Key Commands
# Orient yourself
cat worklogs/handoffs/session-latest.md
# Run tests
pytest tests/ -v
# Try the tool
mini job new --plan examples/example-plan.yaml
mini job list
# View docs
cat README.md
cat TESTING.md
Implementation Preference: Dogfooding via mini
When implementing features or fixes:
- Prefer
minicommands as the primary method — this dogfoods the tool and validates real-world usage - Only fall back to direct code changes when:
- The feature is blocked in
mini(e.g., WebSocket handlers not yet implemented) - The fix requires direct code changes that
minicannot invoke (e.g., schema migrations, internal refactors) - Direct changes make the dogfooding path clearer (rare)
- The feature is blocked in
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.
- 5d ago First seen · 117 lines · 1,156 tokens per session scan A a66eab37e6e2
minimise CLAUDE.md is an instructions file published in the GitHub repository dosatos/minimise (11 stars, last pushed 16d ago), licensed MIT. It adds 1,156 tokens to every session, about $0.0058 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
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.
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).
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.
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
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).