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.
git clone --depth 1 https://github.com/acolomba/pi-claude-marketplaceWrote 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/commands/acolomba/pi-claude-marketplace/analyze-upstream-releases)<a href="https://agentmods.dev/commands/acolomba/pi-claude-marketplace/analyze-upstream-releases"><img src="https://agentmods.dev/badge/commands/acolomba/pi-claude-marketplace/analyze-upstream-releases/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/acolomba/pi-claude-marketplace/analyze-upstream-releases"><img src="https://agentmods.dev/badge/commands/acolomba/pi-claude-marketplace/analyze-upstream-releases.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00052 | $0.02296 |
| Opus 5 | $0.00026 | $0.01148 |
| Sonnet 5 | $0.00010 | $0.00459 |
| Haiku 4.5 | $0.00005 | $0.00230 |
Grade A, and why
analyze-upstream-releases 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 13d 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 — 131 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Upstream release review
Read what our three upstreams shipped in a given window and work out, entry by entry, what it means for pi-claude-marketplace. This is read-only research — it produces a report and a set of recommended follow-ups, and changes nothing on disk.
The three upstreams:
earendil-works/pi— npm@earendil-works/pi-coding-agentnicobailon/pi-subagents— npmpi-subagentsnicobailon/pi-mcp-adapter— npmpi-mcp-adapter
Phase 0 — Resolve the time frame
$ARGUMENTS is an optional time frame. Default to the past 7 days when it is empty. Accept, and normalize to an explicit [start, end] date pair:
- durations —
1w,2w,7d,30d,3m - open-ended —
since 2026-07-01,since v0.12.0(the date that tag was published in this repo) - closed ranges —
2026-07-01..2026-08-01 - informal —
last month,since the last milestone(use.planning/STATE.md'slast_activity)
Compute the boundary dates with date (this is macOS, so BSD date -v-7d +%F; fall back to GNU date -d if that fails), and state the resolved window in the first line of your report. Everything downstream filters on it.
Widen the cap on how many releases you fetch to match the window — a 3-month window needs a larger --limit than a week.
Phase 1 — Gather the releases
For each repo:
gh release list --repo <owner/repo> --limit <N> \
--json tagName,name,publishedAt,isPrerelease,isDraft
Filter by publishedAt inside the window — do not trust --limit ordering alone — then pull the body of each in-window release with gh release view <tag> --repo <owner/repo> --json body.
GitHub releases are not the whole story:
- A repo may tag without cutting a release — check
gh api repos/<owner/repo>/tagsand the repo'sCHANGELOG.md. - npm may lead or lag the tags — cross-check
npm view <pkg> versions --jsonandnpm view <pkg> time --json. - Include prereleases; exclude drafts.
If a repo published nothing in the window, say so in one line and move on.
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.
- 13d ago First seen · 131 lines · 52 tokens per session scan A cd2099c261b8
analyze-upstream-releases is a command published in the GitHub repository acolomba/pi-claude-marketplace (23 stars, last pushed today), licensed MIT. It adds 52 tokens to every session and 2,296 once invoked, about $0.0003 per session on Opus 5. 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 commands, from other repositories
land
Cadence-tick autonomous PR babysitter (CI-fix, resolve, converge, merge, close, release).
ship
Deploy feature through automated staging validation to production with rollback testing.
release-notes
Generate consistent, well-structured release notes from git history. Triggered on release tags following semver patterns (v..) to produce categorized changelog with breaking changes, features, fixes, and contributor attribution.
ship
Ship is the operational release-prep flow for a connected project repo.
release-plan
A release-planning command for a software change. It documents the release scope, rollback plan, gradual or full rollout, and monitoring before waiting for human approval.
rally-merge-pr
You are merging the current branch's PR and syncing the feature branch with main. Follow each step exactly.