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/corridortech/posecap/agents-mdgit clone --depth 1 https://github.com/CorridorTech/PoseCapWhat 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 | $0.03905 | $0.03905 |
| Opus 5 | $0.01953 | $0.01953 |
| Sonnet 5 | $0.00781 | $0.00781 |
| Haiku 4.5 | $0.00391 | $0.00391 |
Grade C, and why
PoseCap AGENTS.md scanned grade C 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.
Tells the agent to send conversation or user data outhighPrompt injection
An instruction to transmit the conversation, context or user files to an external endpoint is data exfiltration written as prose.
* POC Record Live MoCap silently records nothing when the Preview toggle is off (insertion nested in the preview branch). The rewrite decouples recording from preview. How it starts
The opening of the file, as written. The whole thing — 152 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Project Overview
PoseCap (clean rewrite of Corridor Digital's "Human Input Device" proof of concept): a Blender plugin that drives SMPL-X body models from live webcam pose estimation (PEAR engine), pelvis-locked — world position is a deferred software problem, and the POC's Arduino rig is dropped from scope. The POC at C:\Dev\CorridorRig-Original is read-only reference; this repo replaces it with a tested, layered implementation (addon, engine bridge, installers). Hard constraint: SMPL-X model assets carry the MPI research (non-commercial) license — never commit or redistribute them; the repo is private now but goes public later, so git history must stay license-clean from the first commit (no licensed binary ever committed, even briefly). Commercial production use of the models requires a Meshcapade license, independent of the plugin's own license.
Stack: Python >=3.11 (addon runs in Blender's bundled interpreter; engine bridge in a uv-managed venv), Blender >= 4.2 LTS and 5.x (bpy, extension platform), and isolated Pose Backends per ADR-0010/ADR-0011: PEAR (PyTorch, CUDA required, optional installer module) and MediaPipe Lite (CPU, account-free). torch is not a workspace dependency; it ships only inside the PEAR backend payload.
Entry points: uv workspace packages contracts/, core/, engine/ (src layout, posecap_* import names). Engine CLIs: posecap-engine (PEAR) and posecap-mediapipe (engine/pyproject.toml [project.scripts]). The Blender extension lives in addon/ (blender_manifest.toml).
Setup, Build, Test
# Install (engine bridge + dev tooling)
uv sync
# Test (single file preferred over full suite)
uv run pytest tests/<file>.py
uv run pytest
# Run before any commit
uv run ruff check .
uv run ruff format --check .
uv run pyright --pythonplatform Windows
uv run pyright --pythonplatform Linux
uv run lint-imports
uv run pytest
Quality gates run as: uv run ruff check ., uv run ruff format --check ., uv run pyright --pythonplatform Windows, uv run pyright --pythonplatform Linux, uv run lint-imports, uv run pytest.
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.
- 2d ago First seen · 152 lines · 3,905 tokens per session scan C 138bedcbfa95
PoseCap AGENTS.md is an instructions file published in the GitHub repository CorridorTech/PoseCap (190 stars, last pushed 9d ago), licensed Apache-2.0. It adds 3,905 tokens to every session, about $0.0195 per session on Opus 5. A static security scan graded it C with 1 finding (tells the agent to send conversation or user data out). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
buildNext
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
spec-kit AGENTS.md
Instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
langchain AGENTS.md
Instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.