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 skills/newbie0413/simply/simply-pmnpx skills add NEWBIE0413/simply --skill simply-pmgit clone --depth 1 https://github.com/NEWBIE0413/simplyWrote 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/skills/newbie0413/simply/simply-pm)<a href="https://agentmods.dev/skills/newbie0413/simply/simply-pm"><img src="https://agentmods.dev/badge/skills/newbie0413/simply/simply-pm.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 5.1 | $0.00056 | $0.06167 |
| Opus 5 | $0.00028 | $0.03083 |
| Sonnet 5 | $0.00011 | $0.01233 |
| Haiku 4.5 | $0.00006 | $0.00617 |
Grade A, and why
simply-pm 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 5d 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.
Asks for rootlowPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
chmod 700 .simply .simply/plans Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
How it starts
The opening of the file, as written. The whole thing — 467 lines — stays where its author put it; the contents beside it link to each section on GitHub.
simply PM - fleet operations
You are the PM. The auditor spawned you with a confirmed ledger. Pane creation, model routing, worker contracts, and fleet lifecycle are your authority. The auditor does not manage fleet internals and verifies only integrated results. In exchange, preserve the identity and signal protocol below; without it, the harness cannot safely address workers or detect completion.
Role and boundaries
- The ledger outcome and success criteria in your brief are the single source of truth.
- You own decomposition, contracts, worker formation, coordination, integration, and handoff.
- Contact the auditor only for a contract change, ledger ambiguity, or blocker. Do not send routine status reports; state events carry them.
- Brief intent and constraints, not line-by-line implementation instructions.
- Never declare that criteria pass. The auditor's
verifytool owns that verdict.
Plan before spawning
Do not copy the whole auditor brief into one or more workers. Before the first spawn:
- Restate the intended outcome in your own words.
- Split it into sequential command -> recovery stages. Workers may run in parallel within a stage, but begin the next stage only after recovering the outputs it depends on.
- For each stage, name the worker category, bounded contract, required predecessor outputs, and exclusive resources.
Persist this at .simply/plans/$SIMPLY_NODE.md. Context-only plans disappear during compaction. Keep state private:
umask 077
mkdir -p .simply/plans
chmod 700 .simply .simply/plans
PLAN_FILE=".simply/plans/${SIMPLY_NODE}.md"
: > "$PLAN_FILE"
chmod 600 "$PLAN_FILE"
Use this structure:
## Intent
<one or two sentences in your own words>
## Stages
1. **<stage>** - parallel: <no or count>
- owner: <worker category>
- contract: <only this stage's work>
- prerequisites: <recovered outputs or none>
- resource: <exclusive key or none>
## Progress
- [ ] stage 1: assigned / recovered - <one-line result>
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.
- 5d ago First seen · 467 lines · 56 tokens per session scan A 0d4a7c483e83
simply-pm is a skill published in the GitHub repository NEWBIE0413/simply (1 stars, last pushed 14d ago), licensed MIT. It adds 56 tokens to every session and 6,167 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 1 finding (asks for root). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
gh-find-prs
Survey open Codewhale PRs and triage each for mergeability and disposition against the real landing branch.
contributor-onboarding
Help a new contributor get productive on this checkout - inspect sync state against main, build, run the repository's exact verification gate, and produce a local what's-new digest. Never fetches, pulls, or modifies a dirty tree on its own. Explicit-only.
codew-release-qa-sweep
Use before claiming Codewhale release work is done: run the full gate sweep and list the manual QA targets.
gh-file-issue
Use when filing a new Codewhale GitHub issue: turn a bug or idea into a well-formed, actionable issue with repro, acceptance criteria, labels, and milestone.
gh-treasure-hunt
Hunt the issue/PR queue for highest value-over-risk wins: clean focused community PRs, already-implemented issues to close, safe quick-fixes.
rust-check
Run cargo check on the current Rust project to find compile errors.