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.
npx agentmods add instructions/0k-lab/knowledge-capture/agents-mdgit clone --depth 1 https://github.com/0k-lab/knowledge-captureWhat 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 | $0.00122 | $0.00122 |
| Opus 5 | $0.00061 | $0.00061 |
| Sonnet 5 | $0.00024 | $0.00024 |
| Haiku 4.5 | $0.00012 | $0.00012 |
Grade A, and why
knowledge-capture AGENTS.md 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.
What it actually says
AGENTS.md
Project Scope
This project builds an Agent Skill, not a processing system.
Keep SKILL.md concise and put longer details in skills/knowledge-capture/references/.
Maintenance Rules
- Scripts must be deterministic, non-interactive, dependency-free for v0.7, and make no network calls.
- Add no sync behavior, graph/vector database, Obsidian processing, durable memory promotion, or automatic git commits.
- Keep raw captures local-first. Default to repo-local
.capture/raw/unless the user explicitly configures another local output root.
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 · 14 lines · 122 tokens per session scan A 92f66a077023
knowledge-capture AGENTS.md is an instructions file published in the GitHub repository 0k-lab/knowledge-capture (2 stars, last pushed 5d ago), licensed MIT. It adds 122 tokens to every session, about $0.0006 per session on Opus 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 2026-08-31.
Other instructions, from other repositories
FlowBoard AGENTS.md
Instructions for rasimme/FlowBoard, covering flowboard — agent entry point, start here and where things live.
aiwff-runtime AGENTS.md
Instructions for zaxardery8011-design/aiwff-runtime: This repository is a mock-first local runtime. Keep all work inside this repository unless the user explicitly asks for a separate path.
aiwff-runtime CLAUDE.md
Instructions for zaxardery8011-design/aiwff-runtime, covering 大腦配置, 執行規則 and 邊界.
gini-agent AGENTS.md
AGENTS.md instructions for Open-Curiosity/gini-agent, covering gini agent instructions, shape, adrs, boundaries and branches.
barkeep AGENTS.md
Instructions for iannuttall/barkeep, covering agent notes, product rules, repo map, commands and app structure.
Silex AGENTS.md
AGENTS.md instructions for silexlabs/Silex, covering agents.md, tech stack, run it locally, building the desktop app and when writing code for silex (editing source).