ForgeFlow
Copilot instructions1 starsChanged 45 days agoMITView on GitHub
Profile: balanced Source: committed-adapter Lean guidance is advisory. It does not edit settings, install hooks, mutate context, change routing, commit, push, or call the network. FORGEFLOW LEAN SESSION ACTIVE - profile: balanced Prefer reuse, native, standard-library, and project-pattern checks before custom code. Keep lean guidance advisory and preserve explicit requirements, safety, accessibility, validation, and data-loss safeguards. Before custom code, check: current need, stdlib, native platform, installed dependencies, project patterns, then minimum custom code. Prefer deletion, direct code, and fewer files…
In this repository37 other files it gives its agents.
- AGENTS.mdAGENTS.md
- .cursor/rules/forgeflow-lean.mdcCursor rule
- aegis-verifySkill
- agent-chat-offSkill
- agent-chat-onSkill
- auditSkill
- consultSkill
- create-agentSkill
- debateSkill
- discussSkill
- forgeflow-capabilitiesSkill
- forgeflow-consultSkill
- forgeflow-implementSkill
- forgeflow-research-divergence-adviceSkill
- forgeflow-research-divergence-evalSkill
- forgeflow-reviewSkill
- forge-reviewSkill
- implementSkill
- planSkill
- quickSkill
- researchSkill
- shipSkill
- taskSkill
- update-forgeflowSkill
- verifier-verifySkill
- forgeflow-auditSkill
- forgeflow-capabilitiesSkill
- forgeflow-implementSkill
- forgeflow-lean-auditSkill
- forgeflow-lean-debtSkill
- forgeflow-lean-primeSkill
- forgeflow-lean-reviewSkill
- forgeflow-leanSkill
- forgeflow-planSkill
- forgeflow-research-divergence-adviceSkill
- forgeflow-reviewSkill
- forgeflow-shipSkill
The file
We split this copilot-instructions.md into the rules it gives an agent
6 rules. About 0 are common, 6 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈6
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 10
Prefer reuse, native, standard-library, and project-pattern checks before custom code.
- Distinctive: line 11
Keep lean guidance advisory and preserve explicit requirements, safety, accessibility, validation, and data-loss safeguards.
- Distinctive: line 13
Before custom code, check: current need, stdlib, native platform, installed dependencies, project patterns, then minimum custom code.
- Distinctive: line 14
Prefer deletion, direct code, and fewer files when current requirements allow it.
- Distinctive: line 17
Do not simplify away security, accessibility, trust-boundary validation, data-loss prevention, explicit requirements, calibration/tuning …
- Distinctive: line 18
Use implementation notes or lean markers for known ceilings and upgrade triggers.
≈ “Common” is an estimate: at least 1 in 5 of the 3,779 Copilot instructions files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Forgeflow Lean Copilot Instructions
Profile: balanced Source: committed-adapter
Lean guidance is advisory. It does not edit settings, install hooks, mutate context, change routing, commit, push, or call the network.
FORGEFLOW LEAN SESSION ACTIVE - profile: balanced
Prefer reuse, native, standard-library, and project-pattern checks before custom code. Keep lean guidance advisory and preserve explicit requirements, safety, accessibility, validation, and data-loss safeguards.
Before custom code, check: current need, stdlib, native platform, installed dependencies, project patterns, then minimum custom code. Prefer deletion, direct code, and fewer files when current requirements allow it. For complex requests, take the smallest safe path and name the fuller path only when the user needs it.
Do not simplify away security, accessibility, trust-boundary validation, data-loss prevention, explicit requirements, calibration/tuning knobs, or one focused check for non-trivial logic. Use implementation notes or lean markers for known ceilings and upgrade triggers. This guidance is advisory; current user instructions, code evidence, tests, and review findings win.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

