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/assafkip/kipi-system/agents-mdgit clone --depth 1 https://github.com/assafkip/kipi-systemWrote 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/instructions/assafkip/kipi-system/agents-md)<a href="https://agentmods.dev/instructions/assafkip/kipi-system/agents-md"><img src="https://agentmods.dev/badge/instructions/assafkip/kipi-system/agents-md.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 | $0.00744 | $0.00744 |
| Opus 5 | $0.00372 | $0.00372 |
| Sonnet 5 | $0.00149 | $0.00149 |
| Haiku 4.5 | $0.00074 | $0.00074 |
Grade A, and why
kipi-system 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 6d ago.
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.
Copies of this mod
1 near-identical copy found in the catalogue:
- kipi-system CLAUDE.md — 88% identical, 18 lines differ
How it starts
The opening of the file, as written. The whole thing — 44 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Q Entrepreneur OS
@q-system/AGENTS.md
Project Structure
plugins/- Plugin groups: kipi-core (every instance), kipi-ops (GTM), kipi-design (UI).Codex/agents/- Custom agent definitions (preflight, data-ingest, synthesizer, etc.).Codex/rules/- Path-scoped instruction filesq-system/- Core OS (canonical/, marketing/, methodology/, output/, my-project/, memory/)
Conventions
- Never produce fluff - every sentence must carry information or enable action
- Mark unvalidated claims with
{{UNVALIDATED}}or{{NEEDS_PROOF}} - All written output goes through the founder voice skill
- All actionable output follows AUDHD executive function rules (if enabled)
- No filler phrases ("leverage," "innovative," "cutting-edge," "game-changing")
- When something fails because an LLM misinterpreted instructions, the fix must be a deterministic script or code change
- A prompt or skill alone cannot enforce behavior. Enforcement requires a hook, script, test, validator, required check, or executable code. The
prompt-only-enforcement-guard.pyPostToolUse hook blocks prompt-only enforcement claims. - For any task involving more than a single file edit, state the planned approach and wait for OK
- When fixing identified issues, fix exactly what was flagged. No scope expansion.
- Never read or search files outside the current project directory without stating which directory and why
- All product/system changes use the PRD template at
q-system/marketing/templates/prd.md
Commands
/q-morning- Full morning briefing (9-phase agent pipeline)/q-debrief- Post-conversation extraction (highest priority)/q-calibrate- Update canonical files/q-create- Generate specific output (talk tracks, emails, slides, decks)/q-plan- Review and prioritize actions/q-engage- Social engagement mode/q-market-*- Marketing system commands/q-draft- Ad-hoc output generation/q-wrap- Evening health check/q-handoff- Session continuity/q-research- Anti-hallucination research mode/wiring-check- End-of-task gate: verify every change is connected end-to-end. Full rule in.Codex/rules/wiring-check.md/say- Synthesize the previous assistant response to a stable mp3 via OpenAI TTS. Autoplays locally in a new Terminal window (mpv) so your keys drive speed/seek/pause; over SSH, without mpv, or with--no-playit just prints the play command. Manual replay:mpv ~/.config/kipi/say-last.mp3(orsay-play). Over SSH:ssh <mini> 'cat ~/.config/kipi/say-last.mp3' | mpv -./say stopclears stray playback.
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.
- 6d ago First seen · 44 lines · 744 tokens per session scan A e7762a441bea
kipi-system AGENTS.md is an instructions file published in the GitHub repository assafkip/kipi-system (109 stars, last pushed today), licensed MIT. It adds 744 tokens to every session, about $0.0037 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 2026-08-30.
Other instructions, from other repositories
mnemonic memory-files.instructions.md
Instructions for modeled-information-format/mnemonic, covering memory file guidelines (mif level 3), required frontmatter fields, optional temporal fields, optional provenance fields and memory types.
mnemonic plugin-files.instructions.md
Instructions for modeled-information-format/mnemonic, covering claude code plugin file guidelines, commands (commands/.md), skills (skills//skill.md), agents (agents/.md) and general guidelines.
mnemonic python.instructions.md
Instructions for modeled-information-format/mnemonic, covering python code guidelines, style, imports, type hints and error handling.
personalos-boilerplate AGENTS.md
Instructions for vincentmumme/personalos-boilerplate, covering personalos boilerplate, einstieg mit einem nutzer, verbindliche grenzen, maintainer-arbeit and sprache.
brain-starter CLAUDE.md
Instructions for michaeljauk/brain-starter, covering brain repo - claude instructions, purpose, not set up yet?, file placement rules and directory guide.
markdown-agent-vault-ru AGENTS.md
AGENTS.md instructions for dzhokhov/markdown-agent-vault-ru, covering agents.md — правила агента для файлового хранилища, главный принцип, карта папок, загрузка контекста and недосказанные запросы.