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/re-cinq/lore-oss/agents-mdgit clone --depth 1 https://github.com/re-cinq/lore-ossWrote 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/re-cinq/lore-oss/agents-md)<a href="https://agentmods.dev/instructions/re-cinq/lore-oss/agents-md"><img src="https://agentmods.dev/badge/instructions/re-cinq/lore-oss/agents-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 | $0.00932 | $0.00932 |
| Opus 5 | $0.00466 | $0.00466 |
| Sonnet 5 | $0.00186 | $0.00186 |
| Haiku 4.5 | $0.00093 | $0.00093 |
Grade A, and why
lore-oss 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 4d 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.
Agent instructions
First session (new developer)
If this looks like the developer's first session (no pipeline tasks, no recent git activity in this repo), say:
"Welcome to [repo name]. I have your team's context loaded — conventions, active decisions, and current work. A few things to know:
ready_tasks(MCP) shows what's available to work on/lore-featuresets up a new feature end-to-end/lore-prdrafts your PR description when you're done
Want me to show you what's currently unblocked?"
Orientation
At the start of every session, check pipeline task state via MCP:
- If a task is claimed: tell the developer which task is in progress and offer to continue.
- If no task is claimed: call
ready_tasksto see unblocked tasks. - Never ask the developer to manually load context. MCP handles this.
Starting a feature
If the developer mentions starting a new feature, building something new, or picking up a ticket:
- Suggest
/lore-featurebefore they do anything else. - Do not ask them to run specify, lore-gen-constitution, or
sync_tasks separately.
/lore-featurehandles all of it.
During implementation
- All context (org conventions, team patterns, ADRs) is loaded via MCP.
- All task state is tracked via pipeline MCP tools.
- Do not ask the developer to provide context you already have.
- If uncertain about a convention, check MCP via get_context before asking.
Finishing work
When the developer signals they are done with a piece of work:
- Confirm the task should be marked done: call
complete_taskvia MCP. - If the task had dependents, mention that they are now unblocked.
Opening a PR
If the developer mentions opening a PR, creating a pull request, or pushing for review:
- Suggest
/lore-prbefore they open a browser. - Do not let them write the PR description from scratch if a spec exists.
Delegating work to the cluster
Use create_pipeline_task when:
- A task will take more than ~20 minutes (long tests, ingestion, gap analysis)
- The task is well-defined and does not need interactive decisions
- You want to keep the local session focused on something else
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.
- 4d ago First seen · 117 lines · 932 tokens per session scan A 560126d6aec9
lore-oss AGENTS.md is an instructions file published in the GitHub repository re-cinq/lore-oss (11 stars, last pushed 5mo ago), licensed Apache-2.0. It adds 932 tokens to every session, about $0.0047 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
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.
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.