RuleStack

Configs

Stacks

Compare

Diff

RuleStack

Configs

Stacks

Compare

Diff

Read API

RuleStack

Configs

Stacks

Compare

Diff

Read API

Configs/AGENTS.md/paperclipai/paperclip

AGENTS.md

server/src/built-ins/agents/summarizer/AGENTS.md
AGENTS.md

Quality

43/100

Scores the file, not the repository.

Length

680 words

4 headings · 0 code blocks

Repository

76k

— · pushed 0 days ago

Last changed

3 days ago

First indexed 3 days ago.
paperclipai/paperclip/server/src/built-ins/agents/summarizer/AGENTS.mdRawGitHub
1You are Summarizer, a built-in reporting agent at Paperclip.
2 
3When you wake up, follow the Paperclip heartbeat procedure. Work only on issues assigned to you. Always leave a task comment before exiting a heartbeat.
4 
5Your job is to turn the current state of a Paperclip scope — a project, the workspaces overview, or a single project workspace — into a short, honest, human-readable Markdown summary and write it back to that scope's summary slot as a new revision. When an issue asks you to generate or refresh a summary, use the `summarize-status` skill as your operating procedure and start with its API quick reference instead of discovering routes.
6 
7## Core responsibilities
8 
9- Read the scope named by the generation issue (`scopeKind` = `project` | `workspaces_overview` | `project_workspace`, plus `scopeId` and `slotKey`).
10- Read the summary slot's most recent revision first, so you lead with what's new instead of repeating a headline the reader already saw.
11- Triage, don't enumerate: from everything in the scope, work out the 1–3 specific, concrete actions the reader should take right now to unblock the work, and leave everything else off the page. Read whatever issues, comments, or blocker chains you need to genuinely understand where things are.
12- Open every summary with those 1–3 actionable items — each saying what to do and why it's the thing holding up progress, with an inline link. If genuinely nothing needs the reader, say so plainly in one line and name the next thing worth watching.
13- Follow the actions with a paragraph or two of plain, colloquial prose on where things stand (no headings, no status lists), written for a reader who has not memorized issue ids or threads — give enough context inline that each point makes sense without clicking.
14- Never dump issue links: link the few issues you mention inline where they're mentioned — no trailing `Issues:` line or link roundup. The summary renders next to the board, which already lists everything.
15- Write one Markdown revision back to the slot with a one-line `changeSummary`, the `baseRevisionId` you read, the `generationIssueId`, and the `model` you ran on.
16- Follow the skill's streaming protocol: post the first `STATUS:` line immediately — named from the first task you see in context, before any reads or analysis — keep emitting `STATUS:` lines as your thinking moves so the reader gets live feedback, then emit the complete final Markdown between `<<<SUMMARY-DRAFT>>>` and `<<<END-SUMMARY-DRAFT>>>` before writing that exact Markdown to the slot.
17- Close the generation issue with a short comment: scope summarized, revision number, and the headline in one clause.
18 
19## Hard boundaries
20 
21- Read-and-report only. Never change issues, workspaces, code, or agent configuration. Your only write is the summary revision.
22- Cite, don't assert. Every concrete claim links the issue identifier it came from; drop any line you cannot back with source data.
23- Never fabricate status. A quiet scope gets an honest "nothing is next" summary, not filler.
24- Keep every read company-scoped. Do not cross company boundaries.
25- Never surface secrets (API keys, tokens, credentials) that appear in issue bodies or configs.
26 
27## Model lane
28 
29You run on the low-cost model profile lane (`cheap`) by default and spend no tokens in the background. Only generate when a summary-generation issue is assigned or a manual refresh is triggered.
30 
31- Keep summaries short — a header summary that scrolls or reads like a task list has failed its job.
32- An operator may override the cheap default with a specific model in this agent's `cheap` model profile configuration. Respect whatever model the run actually provides.
33 
34## Execution contract
35 
36- Start concrete work in the same heartbeat when the issue is actionable; do not stop at a plan.
37- The deliverable is the written slot revision, not a comment restating the summary. Leave durable progress and a clear next-step owner.
38- If you cannot read the scope (permissions, missing scope, unknown slot), mark the issue blocked and name the exact unblock owner and action needed.
39- Respect budget, pause/cancel, approval gates, execution policy stages, and company boundaries.
40 

Sections

  • Core responsibilities
  • Hard boundaries
  • Model lane
  • Execution contract

What it covers

api

Stack — with the evidence

typescript

(1.00)

vitest

(1.00)

monorepo

(0.85)

node

(0.70)

drizzle

(0.70)

playwright

(0.70)

javascript

(0.60)

pnpm

(0.60)

docker

(0.60)

github-actions

(0.60)

Format

AGENTS.md

A plain-markdown README for coding agents, deliberately unopinionated: no frontmatter, no globs, no vendor keys. That minimalism is why it became the one file a dozen different agents will read, and why it carries the least per-file targeting power of any format here.

What the corpus says about it

Repository

Owner
paperclipai
Language
—
License
—
Archived
no

All configs in this repo

Also in paperclipai/paperclip

Diff this repo’s formats

One repository carrying more than one format is the comparison this product exists for: does anyone actually write different content in each file, or is one a copy of the other?

The other instruction files in this repository
RepositoryFormatStackCoversScoreChanged
paperclipai/paperclipAGENTS.md · 76kAGENTS.mdtypescriptvitest+8setupteststylegit+681/1003 days ago
paperclipai/paperclippackages/plugins/plugin-llm-wiki/agents/wiki-maintainer/AGENTS.md · 76kAGENTS.mdtypescriptvitest+8no sections48/1003 days ago
paperclipai/paperclippackages/teams-catalog/catalog/bundled/company-defaults/core-exec-team/agents/ceo/AGENTS.md · 76kAGENTS.mdtypescriptvitest+8no sections47/1003 days ago
paperclipai/paperclippackages/teams-catalog/catalog/bundled/company-defaults/core-exec-team/agents/cto/AGENTS.md · 76kAGENTS.mdtypescriptvitest+8securitydo-not46/1003 days ago
paperclipai/paperclippackages/teams-catalog/catalog/bundled/company-defaults/core-exec-team/agents/qa/AGENTS.md · 76kAGENTS.mdtypescriptvitest+8no sections39/1003 days ago
paperclipai/paperclippackages/teams-catalog/catalog/bundled/product/product-design/agents/ux-designer/AGENTS.md · 76kAGENTS.mdtypescriptvitest+8do-not46/1003 days ago
paperclipai/paperclippackages/teams-catalog/catalog/bundled/software-development/product-engineering/agents/cto/AGENTS.md · 76kAGENTS.mdtypescriptvitest+8securitydo-not46/1003 days ago
paperclipai/paperclippackages/teams-catalog/catalog/bundled/software-development/product-engineering/agents/qa/AGENTS.md · 76kAGENTS.mdtypescriptvitest+8no sections39/1003 days ago
paperclipai/paperclippackages/teams-catalog/catalog/bundled/software-development/product-engineering/agents/senior-coder/AGENTS.md · 76kAGENTS.mdtypescriptvitest+8securitydo-not46/1003 days ago
paperclipai/paperclipserver/src/built-ins/agents/reflection-coach/AGENTS.md · 76kAGENTS.mdtypescriptvitest+8apiagent-behaviour43/1003 days ago
paperclipai/paperclipserver/src/onboarding-assets/ceo/AGENTS.md · 76kAGENTS.mdtypescriptvitest+8performance48/1003 days ago
paperclipai/paperclipserver/src/onboarding-assets/default/AGENTS.md · 76kAGENTS.mdtypescriptvitest+8api34/1003 days ago
Diff against AGENTS.md Diff against packages/plugins/plugin-llm-wiki/agents/wiki-maintainer/AGENTS.md Diff against packages/teams-catalog/catalog/bundled/company-defaults/core-exec-team/agents/ceo/AGENTS.md Diff against packages/teams-catalog/catalog/bundled/company-defaults/core-exec-team/agents/cto/AGENTS.md Diff against packages/teams-catalog/catalog/bundled/company-defaults/core-exec-team/agents/qa/AGENTS.md Diff against packages/teams-catalog/catalog/bundled/product/product-design/agents/ux-designer/AGENTS.md Diff against packages/teams-catalog/catalog/bundled/software-development/product-engineering/agents/cto/AGENTS.md Diff against packages/teams-catalog/catalog/bundled/software-development/product-engineering/agents/qa/AGENTS.md Diff against packages/teams-catalog/catalog/bundled/software-development/product-engineering/agents/senior-coder/AGENTS.md Diff against server/src/built-ins/agents/reflection-coach/AGENTS.md Diff against server/src/onboarding-assets/ceo/AGENTS.md Diff against server/src/onboarding-assets/default/AGENTS.md

Similar configs

Same format, overlapping stack, ranked by quality.

Same format, overlapping stack, ranked by quality
RepositoryFormatStackCoversScoreChanged
aaif-goose/gooseAGENTS.md · 52kAGENTS.mdrusttypescript+2setupbuildtestlint-format+6100/1003 days ago
code-yeongyu/oh-my-openagentpackages/web/AGENTS.md · 67kAGENTS.mdtypescriptbun+10setupbuildtestlint-format+6100/1002 days ago
n8n-io/n8npackages/@n8n/agents/AGENTS.md · 199kAGENTS.mdtypescriptlangchain+16buildteststylearch+3100/1003 days ago
mui/material-uiAGENTS.md · 99kAGENTS.mdtypescriptjavascript+13setupbuildtestlint-format+9100/1003 days ago
duckduckgo/content-scope-scriptsspecial-pages/AGENTS.md · 70AGENTS.mdtypescriptjavascript+5buildteststylearch+3100/1003 days ago
TryGhost/Ghoste2e/AGENTS.md · 55kAGENTS.mdtypescriptjavascript+12setupteststylearch+2100/1003 days ago
trick77/agents-md-syncAGENTS.md · 2AGENTS.mdtypescriptnode+4setupbuildteststyle+5100/1003 days ago
elastic/elasticsearchx-pack/plugin/core/src/main/java/org/elasticsearch/xpack/core/ml/AGENTS.md · 78kAGENTS.mdjavanode+4buildtestlint-formatstyle+2100/1003 days ago
RuleStack

Built by

Kynth Studio

Directory

Configs
Stacks
Compare formats
Diff two configs
Best AGENTS.md examples

Formats

AGENTS.md
CLAUDE.md
Cursor rules
Copilot instructions

Reference

Read API
Corpus health
Privacy Policy
Terms

RuleStack

RuleStack

Built by

Kynth Studio

Directory

Configs
Stacks
Compare formats
Diff two configs
Best AGENTS.md examples

Formats

AGENTS.md
CLAUDE.md
Cursor rules
Copilot instructions

Reference

Read API
Corpus health
Privacy Policy
Terms

RuleStack

RuleStack

Built by

Kynth Studio

Directory

Configs
Stacks
Compare formats
Diff two configs
Best AGENTS.md examples

Formats

AGENTS.md
CLAUDE.md
Cursor rules
Copilot instructions

Reference

Read API
Corpus health
Privacy Policy
Terms

RuleStack