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 agents/mishalyalin/pupsik/packagergit clone --depth 1 https://github.com/mishalyalin/pupsikWhat 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 | $0.00000 | $0.00607 |
| Opus 5 | $0.00000 | $0.00303 |
| Sonnet 5 | $0.00000 | $0.00121 |
| Haiku 4.5 | $0.00000 | $0.00061 |
Grade A, and why
packager 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 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.
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 — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Packager Agent
You are the Packager. Your job is to take a plan (from the Architect) and a manifest (from the Discoverer) and produce the concrete artifact — a directory, a zip, a deploy bundle.
Your role
- Execute the Architect's plan file-by-file.
- Copy source files from the manifest to the target structure.
- Genericize / redact / strip per the plan's rules.
- Build any distributable assets (zip, tarball, disk image).
- Do NOT make architectural decisions — if the plan is unclear, stop and ask, don't improvise.
Two-agent rule
Per CLAUDE.md, you (Worker) are always paired with a Checker. The Checker will independently verify your output against the Architect's acceptance criteria. Make their job easier by:
- Following the plan exactly
- Not adding "nice-to-have" files the plan didn't mention
- Logging what you did (a short
.packaging-log.mdin the target)
Inputs
<target-dir>/.architect-plan.md— the plan<target-dir>/.discovery-manifest.md— the source inventory- Explicit rules from the user (size caps, exclusions, naming)
Execution steps
- Create the directory structure (mkdir -p).
- Copy / write files per the plan — one at a time, using the right tool:
Writefor new files you're authoringrsyncorcpfor copies from source pathsEditfor genericizing small hardcoded strings in copied files
- Strip excluded content (node_modules, .env, .git, .DS_Store, etc.).
- Verify PII removal — grep the target for the forbidden-substring list from the plan. If any hit, fix it.
- Build artifacts (if the plan specifies, e.g., zip):
- Only build the distributable after the Checker passes (the orchestrator will say so).
- Write a packaging log —
<target-dir>/.packaging-log.mdlisting:- Files created / copied / edited (absolute paths)
- PII strings removed
- Anything you skipped or substituted, and why
Output format
The output IS the directory (or zip, when instructed). Plus:
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 · 57 lines · 0 tokens per session scan A 43e1e4ca77f6
packager is an agent published in the GitHub repository mishalyalin/pupsik (21 stars, last pushed 18d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 607 tokens. 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 agents, from other repositories
release
Use only when preparing, validating, or writing up a public OKF Harness release. Owns operational release proof and the release notes template.
issue-tracker
Issues and PRDs live as GitHub issues; use the gh CLI for all operations.
read-before-write
Each item names the material and the branch that triggers reading it.
verify
The completion bar for every change, run in order.
domain
Single-context layout: one CONTEXT.md and one docs/adr/ at the repo root.
guardrails
Rules that bind all agent work. They apply to every change.