agentmods.dev

PlanExe AGENTS.md

Repository instructions for PlanExe, a system made of services and shared packages that runs planning pipelines through web interfaces, workers, databases, and MCP connections. They map the architecture and define compatibility rules for APIs, database models, and task identifiers.

In plain words
What is it for?
Use them to modify PlanExe services, preserve shared contracts, update workers or interfaces, and verify changes across the system.
Why use it?
They help developers change one service without breaking shared data models, existing API clients, or saved planning workflows.

Instructions file for CodexOpenCode

398 3d ago A scan 1,637 tokens original MIT
View the source file PlanExeOrg/PlanExe
Install

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.

agentmods
npx agentmods add instructions/planexeorg/planexe/agents-md
Clone the repo
git clone --depth 1 https://github.com/PlanExeOrg/PlanExe

Made for: Codex, OpenCode.

Per session 1,637 This file is loaded in full into every session.
When invoked 1,637 The same file — it is already loaded in full.
Security scan A 1 finding. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.01637 $0.01637
Opus 5 $0.00818 $0.00818
Sonnet 5 $0.00327 $0.00327
Haiku 4.5 $0.00164 $0.00164

Measured 2d ago against content hash 2aeed8bd37a2, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

PlanExe AGENTS.md scanned grade A with 1 finding 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 2d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

- Prefer unit tests over manual curl/server checks.
AGENTS.md · 127 lines

How it starts

The opening of the file, as written. The whole thing — 127 lines — stays where its author put it; the contents beside it link to each section on GitHub.

PlanExe agent instructions

Scope: repo-level guardrails for PlanExe services and shared packages. Always check the package-level AGENTS.md for file-specific rules (use rg --files -g 'AGENTS.md' if you are unsure).

Repo architecture map

  • database_api: shared SQLAlchemy models for DB-backed services.
  • worker_plan/worker_plan_api: shared API types/helpers (must stay lightweight).
  • worker_plan: FastAPI service that runs the pipeline.
  • frontend_multi_user: Flask UI (hosted mode) + Postgres.
  • worker_plan_database: DB-backed worker that polls tasks.
  • mcp_cloud: MCP stdio server + HTTP wrapper; primary cloud deployment, secondary Docker setup for advanced users, tertiary venv workflow for developers; bridges MCP tools to PlanExe DB/worker_plan.

Shared contracts

  • Keep worker_plan HTTP endpoints and response shapes backward compatible.
  • Preserve shared SQLAlchemy models in database_api (nullable defaults for new columns).
  • Run directory naming defaults live in worker_plan/worker_plan_api/generate_run_id.py. Verify in code before changing run-id formats.
  • Keep prompt catalog UUIDs stable when used as defaults; they live in worker_plan/worker_plan_api/prompt/data/*.jsonl.

Hard rules (agent safety)

  • Never commit directly to main. Always create a feature branch (e.g. feat/short-description, fix/short-description) and commit there. Push the branch and open a PR so CI can verify the changes.
  • Do not add real API keys or passwords to .env, .env.*, or any llm_config/*.json file.
  • Treat track_activity.jsonl as sensitive (may contain API keys/tokens). Never expose it to end users. Store track_activity.jsonl in PlanItem.run_track_activity_jsonl and keep it out of downloadable zips at artifact creation time. Legacy snapshots may be sanitized at download time, but new snapshots should be served directly without unzip/recompress.
  • Shared packages (database_api, worker_plan_api) must not import service apps (frontend_*, worker_plan_database, worker_plan.app).
  • If a service needs shared logic, move it into a shared package rather than importing across service boundaries.

Read the full file on GitHub · 127 lines

Changes

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.

  1. 2d ago First seen · 127 lines · 1,637 tokens per session scan A 2aeed8bd37a2

Subscribe to this mod's changes

PlanExe AGENTS.md is an instructions file published in the GitHub repository PlanExeOrg/PlanExe (398 stars, last pushed 3d ago), licensed MIT. It adds 1,637 tokens to every session, about $0.0082 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

DatabasesLlamaIndexPlanningaiollamaopenrouterplanner
Related

Other instructions, from other repositories

claude-code CLAUDE.md

Instructions for Pushpenderrathore/claude-code: IMPORTANT: Ensure you’ve thoroughly reviewed the AGENTS.md file before beginning any work.

Pushpenderrathore/claude-code · 23 tokens

claude-code AGENTS.md

Instructions for Pushpenderrathore/claude-code, covering agentic directive, coding environment, identity & context, architecture principles and cognitive workflow.

Pushpenderrathore/claude-code · 943 tokens

ollama CLAUDE.md

Claude Code instructions for ollama/ollama: See AGENTS.md for the shared agent instructions for this repository.

ollama/ollama · 21 tokens

pocketpaw CLAUDE.md

Instructions for pocketpaw/pocketpaw, covering claude.md, project overview, knowledge base, search the kb from terminal and show a specific module's wiki.

pocketpaw/pocketpaw · 2,994 tokens

codexia AGENTS.md

Instructions for milisp/codexia, covering agents.md, project info, project tech, common commands and project structure.

milisp/codexia · 656 tokens

rikkahub AGENTS.md

AGENTS.md instructions for rikkahub/rikkahub, covering repository guidelines, project overview, build, test, and development commands, module structure and concepts.

rikkahub/rikkahub · 997 tokens