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/offendingcommit/openconcho/agents-mdgit clone --depth 1 https://github.com/offendingcommit/openconchoWhat 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 | $0.01298 | $0.01298 |
| Opus 5 | $0.00649 | $0.00649 |
| Sonnet 5 | $0.00260 | $0.00260 |
| Haiku 4.5 | $0.00130 | $0.00130 |
Grade A, and why
openconcho 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 — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.
openconcho
Frontend UI for self-hosted Honcho instances — browse memories, peers, sessions, conclusions, and chat with memory context. Ships as a web app (@openconcho/web) and a Tauri desktop wrapper (@openconcho/desktop).
Commands
make is the canonical interface; it shells out to pnpm scripts which shell out to turborepo. CI calls the same targets — make help lists everything.
| Command | Purpose |
|---|---|
make bootstrap |
Install deps + Playwright Chromium (run once after clone) |
make dev-web |
Vite dev server on http://localhost:5173 |
make dev-desktop (or make dev) |
Tauri desktop app |
make build |
Turbo: build web + desktop |
make lint |
Biome check |
make typecheck |
tsc --noEmit |
make test |
Vitest (unit + integration), excludes e2e/ |
make test-e2e |
Playwright e2e (uncached) |
make smoke-docker |
Local: build image + hermetic smoke test of the /api proxy (Docker required) |
make up |
Run the web container from source (dev-forward, builds) at :8080 |
make prod |
Run the web container from the published image (pulls ghcr…:latest) |
make down |
Stop + remove the web container (dev or prod) |
make clean |
down + remove the locally built image |
make check |
lint + typecheck + test |
pnpm --filter @openconcho/desktop cargo-check |
Local Rust/Tauri compile check before pushing desktop changes |
pnpm --filter @openconcho/web generate:api |
Regen src/api/schema.d.ts from openapi.json |
Structure
| Path | Purpose |
|---|---|
packages/web/ |
Vite + React 19 + TanStack Router/Query SPA |
packages/web/src/routes/ |
TanStack Router file-based routes (flat-route syntax) |
packages/web/src/components/ |
Feature components grouped by domain |
packages/web/src/api/ |
openapi-fetch client + TanStack Query hooks |
packages/web/src/lib/ |
Config (localStorage) + theme utilities |
packages/web/src/hooks/ |
Custom React hooks |
packages/web/src/test/ |
Vitest unit/integration tests + setup |
packages/web/e2e/ |
Playwright e2e specs |
packages/desktop/ |
Tauri shell that bundles the built web app |
charts/openconcho/ |
Helm 3 chart for self-hosting on Kubernetes (OCI artifact on GHCR) |
.claude/rules/ |
Coding conventions (auto-loaded; stack-agnostic, applies to all agents) |
docs/ |
Architecture and references |
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 · 84 lines · 1,298 tokens per session scan A 4c9960c04278
openconcho AGENTS.md is an instructions file published in the GitHub repository offendingcommit/openconcho (165 stars, last pushed 8d ago), licensed MIT. It adds 1,298 tokens to every session, about $0.0065 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
reactive-resume copilot-instructions.md
Instructions for amruthpillai/reactive-resume: Respond terse like smart caveman. All technical substance stay. Only fluff die.
reactive-resume AGENTS.md
Instructions for amruthpillai/reactive-resume, covering skill loading, graphify, agents.md, agent skills and ownership map.
kaneo AGENTS.md
Instructions for usekaneo/kaneo, covering kaneo agent guide, principles, architecture, boundaries that must hold and follow a change through.
kaneo CLAUDE.md
Instructions for usekaneo/kaneo, a project described as: 🎯 All you need. Nothing you don't. Open source project management that works for you, not against you.
deepseek-pp AGENTS.md
Instructions for zhu1090093659/deepseek-pp, covering deepseek++ project agent instructions, scope, product context, truth sources and collaboration rules.
ProductFlow AGENTS.md
Instructions for yuqie6/ProductFlow, covering trellis instructions, repository guidelines, project structure & module organization, build, test, and development commands and coding style & naming conventions.