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 commands/openplanr/planr-pipeline/statusgit clone --depth 1 https://github.com/openplanr/planr-pipelineWrote 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/openplanr/planr-pipeline/status)<a href="https://agentmods.dev/commands/openplanr/planr-pipeline/status"><img src="https://agentmods.dev/badge/commands/openplanr/planr-pipeline/status.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 | $0.00035 | $0.01758 |
| Opus 5 | $0.00017 | $0.00879 |
| Sonnet 5 | $0.00007 | $0.00352 |
| Haiku 4.5 | $0.00003 | $0.00176 |
Grade A, and why
status 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 6d 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 — 137 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/planr-pipeline:status [slug]
Read-only. Never mutates disk. Fatals use procedures/fatal-error-format.md.
Two modes:
- No slug → whole-project delivery report (Step A): every Spec / Backlog item / Quick Task rolled up by status, cross-referenced with GitHub PRs + Linear from frontmatter, with a Summary and an Outstanding work section.
- Slug → pipeline rollup for that spec/feature (Steps 0–3: marker, story/task counts, failures).
Step A — No slug: whole-project delivery report (v0.18.x parity)
The planr CLI is the deterministic engine for this report (planr status,
src/services/delivery-status-service.ts); the plugin delegates to it so the two surfaces can
never drift. Only when the CLI is absent do you compose the same report natively.
A.1 — Delegate when the CLI is installed AND new enough (preferred).
command -v planr && planr --version
The delivery report shipped in CLI 1.7.2 — an older planr would print the legacy tree
instead. Delegate only when the version is ≥ 1.7.2 (compare with
printf '%s\n1.7.2\n' "$(planr --version)" | sort -V | head -1 → must print 1.7.2). If so, run
planr status --md (add --github / --linear only if the user explicitly asked for live
cross-referencing) and print its output verbatim. Done — do not re-derive or "improve" the
numbers; one engine, one truth.
A.2 — Fallback (no CLI, or CLI < 1.7.2): compose the same report from disk. Read-only,
deterministic — never invent a status. When falling back because the CLI is outdated, append one
line: Tip: npm i -g openplanr@latest enables the native engine (planr status --md).
- Enumerate (mode per
procedures/mode-detection.md):- Specs:
.planr/specs/SPEC-*/SPEC-*.mdfrontmatter →id,title,status(default mode:output/feats/feat-*/with their.pipeline-shippedmarkers). - Backlog:
.planr/backlog/*.md→id,title,status,priority. - Quick tasks:
.planr/quick/*.md→id,title,status+ checkbox counts (- [x]/- [ ]).
- Specs:
- Classify every item: done (
done|closed|completed|shipped|released) · addressed (promoted|superseded— resolved without being done; NOT outstanding, and never counted as done) · outstanding (everything else). - Cross-reference from frontmatter:
linearIssueIdentifier(+linearStatusReconciledas its state),githubIssue. Ifghis authenticated you MAY best-effort correlate PRs by searching the artifact id in PR titles (gh pr list --search "<ID>" --state all --json number,title,mergedAt); label it best-effort, never as authoritative. - Render exactly this shape (the same as
planr status --md):# <project> — Delivery Status+ a source-of-truth note## Summary— per category:**<Label>:** N done [+ M promoted/superseded] — T total, then**Outstanding:** none | N- One
## <Category>table per non-empty category:| ID | Status | Title | Progress | PR | Linear | ## Outstanding work— list each open item (**ID** title — _status_), orNone — every item is done or addressed (promoted/superseded).
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.
- 6d ago First seen · 137 lines · 35 tokens per session scan A 5e6d614deca5
status is a command published in the GitHub repository openplanr/planr-pipeline (2 stars, last pushed 1mo ago), licensed MIT. It adds 35 tokens to every session and 1,758 once invoked, about $0.0002 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 2026-08-31.
Other commands, from other repositories
iteration-drive
Drive the active iteration to completion — Phase 2 Autonomous Execute, Phase 3 iteration-close, Phase 4 Create PR, Phase 5 PR merge-ready loop (prefer babysit/-babysit; optional greploop when repo has it; else CI fallback) until mergeable. Not Done until Phase 5 exit checklist passes.
project-sprint
Execute project-sprint through Core-owned bounded WorkUnits.
octo-schedule
Manage scheduled workflow jobs for the Claude Octopus scheduler.
octo-scheduler
Manage the Claude Octopus scheduled workflow runner daemon.
discover
Run a full product discovery cycle — from outcome definition through opportunity mapping, prioritisation, and experiment design. Use when the team isn't sure what to build next, or before writing a PRD for a complex feature space.
iteration-loop
Autonomous full iteration loop for cloud agents — Phase 1 (code-first auto direction lock + compass/plans + Review & Edit chain) through Phase 2–5 (execute → close → PR → merge-ready). Optional args: direction, scale (S|M|L|XL, default M). Not Done until Phase 5 exit checklist passes. Minimal human intervention; no…