Borrowing it
Nothing to install: this file belongs to srmackey/context-forge. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/srmackey/context-forge/main/AGENTS.mdgit clone --depth 1 https://github.com/srmackey/context-forgeWrote 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/srmackey/context-forge/agents-md)<a href="https://agentmods.dev/instructions/srmackey/context-forge/agents-md"><img src="https://agentmods.dev/badge/instructions/srmackey/context-forge/agents-md/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/instructions/srmackey/context-forge/agents-md"><img src="https://agentmods.dev/badge/instructions/srmackey/context-forge/agents-md.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00929 | $0.00929 |
| Opus 5.5 | $0.00372 | $0.00372 |
| Sonnet 5.5 | $0.00186 | $0.00186 |
| Haiku 4.5 | $0.00093 | $0.00093 |
Grade A, and why
context-forge 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 15d 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 — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — Context Forge
Guidance for agents and contributors working in this repo.
Product. Context Forge is a local MCP server for workspace memory. It stores working files and sitting records as markdown. A derived SQLite+FTS5 index is rebuildable. The store lives under ~/.contextforge/ (override with CONTEXTFORGE_HOME). When CONTEXTFORGE_ROOT points at a folder that has nexus.md, each nexus folder holds its own store at _contextforge/, and a call names an address. The workspace slug stays the folder basename.
Agent stance
You are a careful steward of a small, markdown-first memory MCP. Files on disk are the truth. Prefer the existing tools (bind_workspace, write, write_working, get_pack, search) before adding new ones.
Stack
- Python 3.11+,
uv, FastMCP, Pydantic v2 - Markdown + YAML frontmatter on disk; SQLite + FTS5 is derived
- Tests with pytest under
tests/ uv sync/uv run pytest/uv run contextforge
Invariants
- Two types:
workspace(bound to a folder; the slug is the folder basename) anddocument(a markdown file under that workspace). Paths are the names. No domain ontology in the server. - With
CONTEXTFORGE_ROOTset, the call's workspace is an address. The address selects that nexus's_contextforge/store. A callpier/dockopens dock's records in pier's store only. A bare name resolves only when one node has it. Without the root, one store atCONTEXTFORGE_HOMEbehaves as before. - Two layers, defaulted by path:
sittingsundersittings/,workingeverywhere else. - Every read and write is workspace-scoped. There is no global search.
- Markdown wins.
reindex(internal, on write and bind) rebuilds the index. - Write is explicit. The store does not guess, extract, or lint a document body.
- A sitting that does not call the store misses it.
Privacy
This repo ships no real personal data and no project names from a real install.
- Docs, comments, examples, and tests use fictional workspace vocabulary (
harbor-notes,river-ledger). - Do not commit a real vault's contents, filesystem paths, or the names of a real install's projects.
- Context Forge is part of Domain Prime. Naming and linking the other Domain Prime repos (domainprime, insitu, envoy, brain-forge) is fine. Names from a real install that runs them are not.
- Write grain (what may go in a file) belongs to the bound workspace's owner, not this server.
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.
- 15d ago Changed · +1 lines · +53 tokens per session 2be3daf785ae
- 16d ago Changed · +10 tokens per session 44148e33601f
- 1mo ago Changed · +1 lines · +132 tokens per session 7b5f1ae03525
- 1mo ago Changed · +1 lines · +47 tokens per session 9e4d6e6c6fba
- 1mo ago Changed · +13 tokens per session fbccccdb3587
- 1mo ago Changed · -105 lines · -2,160 tokens per session 12d2aef193fb
- 2mo ago First seen · 162 lines · 2,834 tokens per session scan A d7a67e65c956
context-forge AGENTS.md is an instructions file published in the GitHub repository srmackey/context-forge (0 stars, last pushed 10d ago), licensed MIT. It adds 929 tokens to every session, about $0.0037 per session on Opus 5.5. 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.
context-forge AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| context-forge AGENTS.mdsrmackey/context-forge | Instructions file | 0 | 10d ago | MIT | A | 929 | Codex, OpenCode |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 9,719 | GitHub Copilot |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 5,516 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | yesterday | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | today | MIT | A | 4,680 | Codex, OpenCode |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 3,093 | GitHub Copilot |
| vscode model-prompts.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 2,022 | GitHub Copilot |