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/vunm-io/passdown/agents-mdgit clone --depth 1 https://github.com/vunm-io/passdownWrote 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/vunm-io/passdown/agents-md)<a href="https://agentmods.dev/instructions/vunm-io/passdown/agents-md"><img src="https://agentmods.dev/badge/instructions/vunm-io/passdown/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 | $0.01280 | $0.01280 |
| Opus 5 | $0.00640 | $0.00640 |
| Sonnet 5 | $0.00256 | $0.00256 |
| Haiku 4.5 | $0.00128 | $0.00128 |
Grade B, and why
passdown AGENTS.md scanned grade B 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 3d 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.
Enumerates other installed skillsmediumAgent snooping
Other skills' SKILL.md files reveal prompts, capabilities and secrets that should be invisible to peers.
ls ~/.claude/skills/ | grep passdown How it starts
The opening of the file, as written. The whole thing — 111 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — passdown
Source of truth for agents working in this repo. This is a standalone public
repo (vunm-io/passdown) — it does not inherit from any parent workspace
config, unlike the thin AGENTS.md this project generates for consumers
(see templates/AGENTS.thin.md).
What this repo is
Four workspace-agnostic Claude Code / Kiro skills (passdown-intake,
passdown-dispatch, passdown-handoff, passdown-pickup) plus an OpenSpec workflow schema
(schemas/passdown/) that makes tasks self-contained and dispatchable. See
README.md for the full pitch and docs/design-2026-07-04-passdown-workflow.md
(in the vunm-workspace meta-repo, not here) for the original design.
Branch policy
mainis protected and release-ready. Never push directly tomain.- Use short-lived branches and pull requests:
feat/<topic>orfix/<topic>for normal work.codex/<topic>for Codex-authored work.release/vX.Y.Zis the integration and beta-testing window for the next version: it branches offmainwith a-beta.Nversion bump, feature/fix PRs target it instead ofmain, and testers install the plugin pinned to it (/plugin marketplace add <repo-url>.git#release/vX.Y.Z). Finalize by setting the release version, merging tomainthrough a green PR, tagging, and deleting the branch. Time-box it to one release; work that misses the window waits for the next one.
- No
developand no long-lived version lines such as0.2.x. While passdown is in v0, fixes move forward into the next release instead of maintaining old minor branches. - Require green CI, then squash or rebase into
main. Never create merge commits and never force-pushmain. - One commit = one logical change. Conventional Commits, English, imperative
mood (
fix: ...,feat: ...,ci: ...,docs: ...). - AI attribution is allowed and optional.
Co-Authored-By: <model>,AI-Assisted-By: <tool>andAI-Reviewed-By: <tool>trailers may stay in commit messages and PR bodies; an AI tool's default commit template needs no stripping. The author of record is still the human who owns the change, so never add a redundant selfCo-authored-byfor that same person.
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.
- 3d ago First seen · 111 lines · 1,280 tokens per session scan B ed0a3e93a81e
passdown AGENTS.md is an instructions file published in the GitHub repository vunm-io/passdown (8 stars, last pushed 14d ago), licensed MIT. It adds 1,280 tokens to every session, about $0.0064 per session on Opus 5. A static security scan graded it B with 1 finding (enumerates other installed skills). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
create-conductor-flow CLAUDE.md
Instructions for Jonkimi/create-conductor-flow, covering conductor context and universal file resolution protocol.
create-conductor-flow GEMINI.md
Instructions for Jonkimi/create-conductor-flow, covering conductor context and universal file resolution protocol.
antigravity-testing-kit GEMINI.md
Instructions for anhtester/antigravity-testing-kit, covering gemini ai - global automation agent rules, git pull restriction rule, browser rules (mandatory), 🖥️ viewport & mode and 🔄 thứ tự debug bắt buộc (playwright mcp).
toh-framework CLAUDE.md
Instructions for wasintoh/toh-framework, covering claude.md — toh framework (repo development guide), what this is, everyday commands, verification protocol and single source, transformed per ide.
awesome-copilot-id AGENTS.md
AGENTS.md instructions for GulajavaMinistudio/awesome-copilot-id, covering communication, explanation and documentation, markdown formatting, user communication style and workflow & methodology.
codevira CLAUDE.md
Instructions for sachinshelke/codevira, covering codevira — persistent project memory, when to call which codevira tool, at the start of every session, before modifying any file and before adopting a pattern, library, or naming convention.