Cognee is an AI memory platform that stores information in a self-hosted knowledge graph so agents can retain context across sessions. It ingests data, connects related information, and helps agents retrieve it for reasoning and actions. The catalogue includes skills and instructions that extend agent workflows around Cognee.
Borrowing it
Nothing to install: this file belongs to topoteretes/cognee. 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/topoteretes/cognee/main/.github/prompts/docs_scope_plan.mdgit clone --depth 1 https://github.com/topoteretes/cogneeWrote 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/commands/topoteretes/cognee/docs_scope_plan)<a href="https://agentmods.dev/commands/topoteretes/cognee/docs_scope_plan"><img src="https://agentmods.dev/badge/commands/topoteretes/cognee/docs_scope_plan.svg" alt="Measured on agentmods" 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 | $0.00000 | $0.00481 |
| Opus 5 | $0.00000 | $0.00241 |
| Sonnet 5 | $0.00000 | $0.00096 |
| Haiku 4.5 | $0.00000 | $0.00048 |
Grade A, and why
docs_scope_plan 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 yesterday.
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 — 47 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a documentation scope planner for the Cognee project.
Analyze this merged PR and produce a small documentation edit plan. Do not edit documentation files.
Available resources
- Documentation repo (
./docs-repo): Contains the documentation pages. Use existing.mdand.mdxpages as the primary targets for edits. Read./docs-repo/docs.jsonif it exists to understand the documentation structure. - Cognee source code (current workspace root): Use the source code to verify actual implementation details, defaults, supported options, function signatures, env vars, and behavior.
- Prepared documentation edit scope: Curated source files, docs candidates, documentation signals, assessment summary, and out-of-scope files produced by the workflow.
Planning task
- Read the prepared documentation edit scope first.
- Use the prepared scope as your primary evidence. Do not re-classify the full PR changed-file list.
- Read only the source files listed in
Source Files To Inspectunless one listed file is insufficient to verify a specific planned edit. - Read only the documentation files listed in
Candidate Documentation Filesunless they are clearly the wrong target. - Do not run shell commands or inspect the full diff. If the prepared scope is still too broad, produce a conservative small plan instead of exploring further.
- Treat files listed in
Out Of Scope Filesas skipped unless one is explicitly needed to verify a planned edit. - Identify the smallest docs edit surface that could cover the public-facing changes.
Write the final plan to the scope plan output path provided by the workflow prompt.
The plan must be Markdown with these exact sections:
Documentation Scope Plan
Docs Needed
true or false
Reason
One concise paragraph.
Documentation-Worthy Changes
Bullets. Each bullet must name the change, the source files proving it, and the recommended docs page type.
Files To Edit
Bullets of existing docs files to edit. Use paths relative to docs-repo. Leave empty if none.
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.
- yesterday First seen · 47 lines · 0 tokens per session scan A 158ae32f86cb
docs_scope_plan is a command published in the GitHub repository topoteretes/cognee (30,576 stars, last pushed today), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 481 tokens. 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 2026-09-07.
Other commands, from other repositories
iai-directive
Record a standing order the user typed themselves, as an explicit memory directive.
everme-help
Print a concise EverMe plugin status + reference card.
q-research
Read the research-mode skill's SKILL.md for the full ruleset before proceeding. Follow all constraints, the source lookup cascade, the token budget, and the "what counts as cited" rules exactly.
save
Save a key-value memory entry to persistent storage.
triage-github
Scan GitHub repos for activity, generate a summary, and create actionable GTD tasks.
tour
Tour this project's memory — what's captured, where it lives, how to recall it (core-memory-kit).