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/nearform/lastlight/claude-mdgit clone --depth 1 https://github.com/nearform/lastlightWrote 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/nearform/lastlight/claude-md)<a href="https://agentmods.dev/instructions/nearform/lastlight/claude-md"><img src="https://agentmods.dev/badge/instructions/nearform/lastlight/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 | $0.02378 | $0.02378 |
| Opus 5 | $0.01189 | $0.01189 |
| Sonnet 5 | $0.00476 | $0.00476 |
| Haiku 4.5 | $0.00238 | $0.00238 |
Grade A, and why
lastlight 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 — 144 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Last Light — monorepo orientation
This is the nearform/lastlight monorepo: a pnpm + Turborepo workspace
holding the Last Light GitHub-maintenance agent, its CLI, its docs site, and its
eval harness. It was consolidated from three sibling repos
(lastlight, lastlight-www, lastlight-evals) — see
docs/plans/monorepo-migration/ for the
migration plan and locked decisions.
The full day-to-day dev guide lives in
apps/server/CLAUDE.md(withlastlight-core). Read that for runtime, architecture, commands, env vars, and deployment. Use this file only to find your way around the workspace; each package has its ownCLAUDE.mdfor local detail.
Workspace map
lastlight/ # repo root — private orchestration package (lastlight-monorepo)
├── pnpm-workspace.yaml turbo.json tsconfig.base.json pnpm-lock.yaml .nvmrc (22)
├── instance/ # deployment overlay — gitignored, host-only (present on prod hosts, never in the tree)
├── docs/ # cross-cutting docs (migration plan, RELEASING.md)
├── .github/workflows/ # ci / publish / deploy-www / deploy-evals
├── apps/
│ ├── server/ # lastlight-core — the harness + server + Docker stack + ./evals barrel
│ │ ├── CLAUDE.md # ← the full dev guide
│ │ ├── src/ config/ workflows/ skills/ agent-context/ deploy/ spec/ sandbox/ tests/
│ │ ├── Dockerfile sandbox*.Dockerfile docker-compose.yml docker-bake.hcl
│ │ └── dashboard/ # @lastlight/dashboard — admin SPA (nested, private; CLAUDE.md)
│ ├── www/ # lastlight-www (Astro) → lastlight.dev (private; CLAUDE.md)
│ └── evals/ # lastlight-evals → evals.lastlight.dev (its own CLAUDE.md)
│ └── dashboard/ # @lastlight/evals-dashboard — nested, private (CLAUDE.md)
└── packages/ # each package has its own CLAUDE.md
├── cli/ # published "lastlight" — the lean global bin + host-local server cmds
├── code-facts/ # published "lastlight-code-facts" — deterministic PR analysis (bin: lastlight-facts)
├── shared/ # lastlight-shared — light modules used by cli + core
├── workflow-engine/ # lastlight-workflow-engine — core/ ports/ test-support/
└── agentic-pi/ # published "agentic-pi" — the coding-agent harness core runs in the sandbox
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 · 144 lines · 2,378 tokens per session scan A 16a2b8625cc6
lastlight CLAUDE.md is an instructions file published in the GitHub repository nearform/lastlight (22 stars, last pushed 8d ago), licensed MIT. It adds 2,378 tokens to every session, about $0.0119 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
open-code-review AGENTS.md
AGENTS.md instructions for alibaba/open-code-review, covering agent guidelines for open-code-review, project overview, git commit notes, license headers and code style.
open-code-review CLAUDE.md
Claude Code instructions for alibaba/open-code-review: See AGENTS.md for all project guidelines.
trueforge AGENTS.md
AGENTS.md instructions for truefoundry/trueforge, a project described as: The open-source agent harness - the runtime layer that turns an LLM into a working agent.
dshcode copilot-instructions.md
Copilot instructions for whitelonng/dshcode, a project described as: Community desktop companion for DeepSeek Harness — one-click Electron app for macOS and Windows.
happyclaw AGENTS.md
AGENTS.md instructions for riba2534/happyclaw, covering happyclaw agent instructions and definition of done.
sprawling CLAUDE.md
Instructions for 2youg1/sprawling: See AGENTS.md. It is the whole instruction set for this repository — the loop, what to read first, the five steps of one change, the rules a machine holds, and the language and commit conventions.