insitu AGENTS.md

Project-specific instructions for Insitu, a local MCP server that stores reusable roles, skills, and project-specific working protocols. A role describes how an agent should act, while a skill describes a reusable capability or procedure.

In plain words
What is it for?
Managing project context, roles, skills, versioned packs, installation steps, validation findings, and provenance records.
Why use it?
They define the supported design and prevent the implementation from adding tools or behavior that the project does not specify.

Instructions file for CodexOpenCode

Install

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.

agentmods
npx agentmods add instructions/srmackey/insitu/agents-md
Clone the repo
git clone --depth 1 https://github.com/srmackey/insitu

Made for: Codex, OpenCode.

Per session 822 This file is loaded in full into every session.
When invoked 822 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce 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

Measured yesterday against content hash e337214be546, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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.

AGENTS.md · 48 lines

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 under provenance/<id>.md and are not stanzas. Leftover *.prov.md under stanzas/ 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.
  • materialize writes PROTOCOL.md plus host adapters from config/surfaces.yaml, then mapped skill copies under host skill directories. Never clobber AGENTS.md or CLAUDE.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__.py holds it, pyproject.toml derives it, and a test asserts DESIGN.md agrees.

Read the full file on GitHub · 48 lines

Changes

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.

  1. yesterday First seen · 48 lines · 822 tokens per session scan A e337214be546

Subscribe to this mod's changes

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.