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/soju06/knowpatch/agents-mdgit clone --depth 1 https://github.com/Soju06/knowpatchWhat 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 | $0.00630 | $0.00630 |
| Opus 5 | $0.00315 | $0.00315 |
| Sonnet 5 | $0.00126 | $0.00126 |
| Haiku 4.5 | $0.00063 | $0.00063 |
Grade A, and why
knowpatch 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.
How it starts
The opening of the file, as written. The whole thing — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Knowpatch
Knowledge patch (skill/correction) management CLI for AI coding agents.
Environment
| Item | Value |
|---|---|
| Runtime | Bun |
| Language | TypeScript (strict mode) |
| Package Manager | bun |
| Build | bun run build |
| Test | bun test |
| Type Check | tsc --noEmit |
Project Context
knowpatch handles two kinds of hooks:
| Type | Location | Purpose |
|---|---|---|
| Product hooks | src/hooks/ |
User-facing hooks installed by knowpatch (detect.ts) |
| Dev hooks | .agents/hooks/ |
Quality guardrail hooks for developing this project (Python) |
SKILL.md and corrections/ under skills/knowpatch/ are product files.
Always pass typecheck + tests before modifying skill files.
Code Conventions (Key Points)
- TypeScript strict mode — no
any/unknown - ESM modules,
node:prefix,.jsextension imports - Layer separation:
commands/→core/→ui/(core must not import from upper layers) - Never guess versions/packages — verify via package manager
- Details: code-conventions.md
Quality Gate
Run after every code change:
tsc --noEmit && bun test
Dev hooks track dirty state; the Stop hook blocks if not run.
Project Structure
| Directory | Role |
|---|---|
src/commands/ |
CLI commands (install, uninstall) |
src/core/ |
Business logic (parser, paths, hooks) |
src/ui/ |
Terminal output (palette, spinner, interactive) |
src/hooks/ |
Product hooks (detect.ts) |
skills/knowpatch/ |
Product files — SKILL.md + corrections/ |
tests/ |
bun:test tests |
bin/ |
Build output (gitignored) |
.agents/hooks/ |
Dev hooks (Python) |
.agents/conventions/ |
Coding/authoring standards |
.agents/skills/ |
Skill trigger/guardrail rules |
Convention Index
| Convention | File | Key Content |
|---|---|---|
| Code standards | code-conventions.md | TS strict, layer separation, anti-patterns |
| Skill authoring | skill-authoring.md | Prompt principles, correction quality, YAML rules |
| Document standards | document-standards.md | Size limits, TOC, Progressive Disclosure |
| Git workflow | git-workflow.md | Commit rules, branches, pre-push checks |
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 · 69 lines · 630 tokens per session scan A 3a76266843d8
knowpatch AGENTS.md is an instructions file published in the GitHub repository Soju06/knowpatch (2 stars, last pushed 5mo ago), licensed MIT. It adds 630 tokens to every session, about $0.0032 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
gini-agent AGENTS.md
AGENTS.md instructions for Open-Curiosity/gini-agent, covering gini agent instructions, shape, adrs, boundaries and branches.
bread CLAUDE.md
Instructions for tjakoen/bread, covering claude.md — start here, what this is, start here (reading order), this repo is the stack's control plane — run it and non-negotiables (see conventions for the full rules).
getdesign AGENTS.md
Instructions for MohtashamMurshid/getdesign, covering agents, agent skills, issue tracker, triage labels and domain docs.
agentconfig.org AGENTS.md
Instructions for agentconfig/agentconfig.org, covering agent instructions for agentconfig.org, project overview, target audience, site structure and tech stack.
rosetta command-versions-vs-presence.instructions.md
Instructions for tikoci/rosetta, a project described as: MCP Server with RouterOS docs + commands + products + changelogs, using SQLite-as-RAG, sourced from MikroTik.
titen CLAUDE.md
Instructions for RamaAditya49/titen, covering claude.md, read agents.md first, commands, two runtimes, one core and publishing to npm.