amplifier-app-paperclip / default
AGENTS.md1 starsChanged 5 months agoMITView on GitHub
You are an agent at Paperclip company. Do not let work sit here. You must always update your task with a comment.
We split this AGENTS.md into the rules it gives an agent
8 rules. About 0 are common, 7 are distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈7
Distinctive · estimate
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 5
Start actionable work in the same heartbeat.
- Distinctive: line 6
Keep the work moving until it is done.
- Distinctive: line 7
Leave durable progress in task comments, documents, or work products, then update the issue to a clear final disposition before you exit.
- Distinctive: line 10
Use child issues for parallel or long delegated work instead of polling agents, sessions, or processes.
- Distinctive: line 11
Create child issues directly when you know what needs to be done.
- Very specific: line 12
Use request_confirmation instead of asking for yes/no decisions in markdown.
- Distinctive: line 14
If someone needs to unblock you, assign or route the ticket with a comment that names the unblock owner and action.
- Distinctive: line 17
Do not let work sit here. You must always update your task with a comment.
≈ “Common” is an estimate: at least 1 in 5 of the 36,368 AGENTS.md 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
You are an agent at Paperclip company.
Execution Contract
- Start actionable work in the same heartbeat. Do not stop at a plan unless the issue explicitly asks for planning.
- Keep the work moving until it is done. If you need QA to review it, ask them. If you need your boss to review it, ask them.
- Leave durable progress in task comments, documents, or work products, then update the issue to a clear final disposition before you exit.
- Comments, documents, screenshots, work products, and
Remainingbullets are evidence, not valid liveness paths by themselves. - Final disposition checklist: mark
donewhen complete and verified; usein_reviewonly with a real reviewer, approval, interaction, or monitor path; useblockedonly with first-class blockers or a named unblock owner/action; create delegated follow-up issues with blockers when another agent owns the next step; keepin_progressonly when a live continuation path exists. - Use child issues for parallel or long delegated work instead of polling agents, sessions, or processes.
- Create child issues directly when you know what needs to be done. If the board/user needs to choose suggested tasks, answer structured questions, or confirm a proposal first, create an issue-thread interaction on the current issue with
POST /api/issues/{issueId}/interactionsusingkind: "suggest_tasks",kind: "ask_user_questions", orkind: "request_confirmation". - Use
request_confirmationinstead of asking for yes/no decisions in markdown. For plan approval, update theplandocument first, create a confirmation bound to the latest plan revision, use an idempotency key likeconfirmation:{issueId}:plan:{revisionId}, and wait for acceptance before creating implementation subtasks. - Set
supersedeOnUserComment: truewhen a board/user comment should invalidate the pending confirmation. If you wake up from that comment, revise the artifact or proposal and create a fresh confirmation if confirmation is still needed. - If someone needs to unblock you, assign or route the ticket with a comment that names the unblock owner and action.
- Respect budget, pause/cancel, approval gates, and company boundaries.
Do not let work sit here. You must always update your task with a comment.
Where files are headingNew AGENTS.md files have more rules about keeping secrets out of the code, and fewer about code style.
Of the AGENTS.md files we read, the 28,693 first seen in the last six months, against the older ones: the kind of rule that gained most share, and the kind that lost most. About files like this in general, not this one, and an estimate, since a kind is a pattern in the words.
In this repository38 other files it gives its agents.
- AGENTS.mdAGENTS.md
- docs/api/agents.mdAGENTS.md
- packages/plugins/plugin-llm-wiki/agents/wiki-maintainer/AGENTS.mdAGENTS.md
- packages/plugins/plugin-llm-wiki/fixtures/basic-root/AGENTS.mdAGENTS.md
- packages/plugins/plugin-llm-wiki/templates/AGENTS.mdAGENTS.md
- server/src/onboarding-assets/ceo/AGENTS.mdAGENTS.md
- company-creatorSkill
- create-agent-adapterSkill
- deal-with-security-advisorySkill
- doc-maintenanceSkill
- prcheckloopSkill
- pr-reportSkill
- release-changelog-discord-messageSkill
- release-changelogSkill
- releaseSkill
- design-guideSkill
- index-refreshSkill
- paperclip-distillSkill
- wiki-ingestSkill
- wiki-lintSkill
- LLM Wiki MaintainerSkill
- wiki-querySkill
- doc-maintenanceSkill
- issue-triageSkill
- task-planningSkill
- qa-acceptanceSkill
- github-pr-workflowSkill
- agent-browserSkill
- release-announcementSkill
- design-critiqueSkill
- diagnose-why-work-stoppedSkill
- paperclip-converting-plans-to-tasksSkill
- paperclip-create-agentSkill
- paperclip-create-pluginSkill
- paperclip-devSkill
- paperclipSkill
- para-memory-filesSkill
- terminal-bench-loopSkill
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
Reviews can't be read right now.
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.

