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/srmackey/insitu/agents-mdgit clone --depth 1 https://github.com/srmackey/insituWhat 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 | $0.00822 | $0.00822 |
| Opus 5 | $0.00411 | $0.00411 |
| Sonnet 5 | $0.00164 | $0.00164 |
| Haiku 4.5 | $0.00082 | $0.00082 |
Grade A, and why
insitu 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 yesterday.
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 — 48 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — Insitu
Guidance for agents and contributors working in this repo.
Product. Insitu is a portable MCP server for situated identity: who you are here. It stores reusable stanzas, roles, project-mapped skills, and versioned packs, and composes a project-specific protocol. Complementary to ContextForge (system/dev context). Not a second brain.
Design lock. DESIGN.md is the locked spec (v0.14, 2026-08-30). Implement against it. Role and project authoring, user-gated delete, validate findings, the provenance/ why-log tree, the on-demand rename, pack-install (0.9), project_status (0.10), skills (0.11), pack-skill install (0.12), operator classes plus the on-demand install grain (0.13), and the removal of all git operations (0.14) are in src/. Do not add surface it does not name (search, ACL, rename tools, nested roles, role-carried skills) without an explicit design change.
DESIGN is the current shape, not a settled demand. Best practices, first-principles thinking, optimization, and enabling the operator to iterate quickly should always be considered. Proposing defensible improvements is always in scope.
Agent stance
You are a careful steward of a small, markdown-first MCP. Files on disk are the truth. Insitu runs no git and has no subprocess surface; keep it that way. Prefer the existing primitives (stanza, project map, resolve_protocol) before adding new ones.
Stack
- Python 3.11+,
uv, FastMCP, Pydantic v2 - Markdown + YAML frontmatter on disk; no required database in v1
- Tests with pytest under
tests/ uv sync/uv run pytest/uv run insitu
Invariants
- A protocol is composed, never a catalog row. Session start is
resolve_protocol. - A stanza is one markdown file under the user's vault
stanzas/. Why-logs live underprovenance/<id>.mdand are not stanzas. Leftover*.prov.mdunderstanzas/is also not a stanza. - Project key = working folder basename =
projects/<folder>/. Missing project is a structured miss, not a catalog scan. - Vault root is
INSITU_HOME/--vault/~/.insitu. One vault per process. materializewritesPROTOCOL.mdplus host adapters fromconfig/surfaces.yaml, then mapped skill copies under host skill directories. Never clobberAGENTS.mdorCLAUDE.md.- Insitu never runs git and never shells out. Mutating tools write files and return the paths they wrote. Version-controlling a vault is the operator's business.
- One version number.
src/insitu/__init__.pyholds it,pyproject.tomlderives it, and a test assertsDESIGN.mdagrees.
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.
- yesterday First seen · 48 lines · 822 tokens per session scan A e337214be546
insitu AGENTS.md is an instructions file published in the GitHub repository srmackey/insitu (0 stars, last pushed yesterday), licensed MIT. It adds 822 tokens to every session, about $0.0041 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
llm-context.py CLAUDE.md
Instructions for cyberchitta/llm-context.py, covering claude.md, working notes (gitignored) and draining the field notes.
openrouter-mcp-multimodal AGENTS.md
Instructions for stabgan/openrouter-mcp-multimodal, covering agent instructions, before you ship, releasing (read this before publishing), short version and version files (must all match package.json).
seekstone CLAUDE.md
Instructions for shaqmughal/seekstone, covering claude.md, what this repo is, commands, the harness itself (run after npm install) and architecture.
Plonk AGENTS.md
Instructions for ostapondo/Plonk, covering agent rules, layout, adding a module, build & verify and code style.
mcp-dockhand copilot-review.instructions.md
Instructions for strausmann/mcp-dockhand: When reviewing pull requests in this repository.
second-brain AGENTS.md
Instructions for LindaHaviv/second-brain, covering instructions for ai coding agents, what to read first, the rules (non-negotiable), common tasks, the sanctioned way and enforcement, not just instructions.