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.
git 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/rules/srmackey/context-forge/cursor)<a href="https://agentmods.dev/rules/srmackey/context-forge/cursor"><img src="https://agentmods.dev/badge/rules/srmackey/context-forge/cursor/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/rules/srmackey/context-forge/cursor"><img src="https://agentmods.dev/badge/rules/srmackey/context-forge/cursor.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 | $0.00247 | $0.00247 |
| Opus 5.5 | $0.00099 | $0.00099 |
| Sonnet 5.5 | $0.00049 | $0.00049 |
| Haiku 4.5 | $0.00025 | $0.00025 |
Grade A, and why
cursor 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 29d 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.
What it actually says
Context Forge
Context Forge is a local MCP for workspace memory: working files and sitting records. Markdown under ~/.contextforge/ (override CONTEXTFORGE_HOME). Not a wiki, not standing guidance, not a bulletin.
Tools (workspace-scoped, no global search): get_pack, write, write_working, search, bind_workspace.
- Session start:
get_packfor this workspace. Passpathif it may not be bound yet. - Durable freeze-frame for a successor here:
writesittings/YYYY-MM-DD-slug.md. Not every turn. - Overlay / working files:
write_working. Notwrite. - Lookup the pack missed:
searchin that workspace only. - Bind-only:
bind_workspace. Skip ifget_packalready haspath.
If the contextforge tools are missing, the server is not connected. See the checkout install/mcp.json.examples.md. Do not invent a file store.
A sitting that does not call the store misses it.
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.
- 29d ago First seen · 21 lines · 247 tokens per session scan A cecb9e52797f
cursor is a cursor rule published in the GitHub repository srmackey/context-forge (0 stars, last pushed 8d ago), licensed MIT. It adds 247 tokens to every session, about $0.0010 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 2026-09-17.
Other cursor rules, from other repositories
mempalace-recall-always
Always-on MemPalace recall — search the palace before answering about past work, people, projects, or prior decisions.
dreamd-recall
Recall lessons, decisions, and prior context from the .agent/ memory daemon. Use when starting work in a project that has a .agent/ folder, when the user references a past decision, or when you are about to make a choice that has a documented prior.
session-memory
Use at conversation wrap-up or when the user explicitly indicates end-of-session — capture residual lessons not captured in-flight.
common_memory_bank
I am Cursor, an expert software engineer with a unique characteristic: my memory resets completely between sessions. This isn't a limitation - it's what drives me to maintain perfect documentation. After each reset, I rely ENTIRELY on my Memory Bank to understand the project and continue work effectively. I MUST read…
self-improving-obsidian-llm-wiki
LLM Wiki OS operating rules.
memsprout
Cursor rule "memsprout" from memsprout/agents, covering using memsprout, search first, capturing, spaces and topics and files.