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 skills add VandanaAjayDubey111/great-pm --skill done-blockedgit clone --depth 1 https://github.com/VandanaAjayDubey111/great-pmWrote 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/vandanaajaydubey111/great-pm/done-blocked)<a href="https://agentmods.dev/skills/vandanaajaydubey111/great-pm/done-blocked"><img src="https://agentmods.dev/badge/skills/vandanaajaydubey111/great-pm/done-blocked/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/skills/vandanaajaydubey111/great-pm/done-blocked"><img src="https://agentmods.dev/badge/skills/vandanaajaydubey111/great-pm/done-blocked.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 | $0.00054 | $0.01177 |
| Opus 5.5 | $0.00022 | $0.00471 |
| Sonnet 5.5 | $0.00011 | $0.00235 |
| Haiku 4.5 | $0.00005 | $0.00118 |
Grade A, and why
done-blocked 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 1mo 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 — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Codex host binding
- Treat references to Claude slash workflows as the equivalently named Codex skill.
- Before delegating to any specialist, read the
great-pm-runtimeskill and the selected packaged role file. - Treat "invoke", "assign", "delegate", "spawn", and source Agent-tool instructions as a required Codex
spawn_agentcall with that role and a bounded assignment. - For the spawn tool's
task_nameoragent_nameidentifier, replace canonical role-name hyphens with underscores (query-refiner-pm→query_refiner_pm). Keep canonical names unchanged in prompts, filenames, verdict logs, and user-facing output; this is an internal identifier mapping, not a role rename. - Store every returned agent identifier. Never call a wait tool until a spawn has returned an identifier, and wait only on identifiers returned by successful spawns.
- If
spawn_agentis unavailable or a spawn fails, report BLOCKED; do not impersonate the specialist or wait on an empty agent set. - Resolve bundled paths from the installed GreatPM plugin root.
- Ignore Claude-only model aliases, colors, turn limits, and tool allowlists.
- Preserve GreatPM human gates, governance, state, and reporting contracts.
DONE / BLOCKED Reporting Contract
Terminal status is exactly two states, and BLOCKED requires specific evidence — not vague obstruction reports.
The contract
Every great-pm agent's final handoff line is one of:
DONE: <one-sentence summary of what was produced>
artifact: <path to the draft/report produced>
next: <who picks this up — pm-lead, a gate, the human>
BLOCKED: <one-sentence summary of the obstacle>
tried: <what was attempted — files read, agents consulted>
failed_because: <concrete reason — not "unclear", not "complex">
need: <specific unblock — a human decision, a missing input, another agent>
Hard rules
- No third state. "Mostly done", "done with caveats" -> choose. If a caveat blocks the next stage -> BLOCKED. If cosmetic -> DONE (log it, move on).
- BLOCKED requires three fields — tried + failed_because + need. Missing any -> the verdict is rejected; re-report.
- Silence is not DONE. An agent that stops with no terminal line is treated as BLOCKED (failed_because: silent — no terminal verdict written).
- failed_because must be concrete. Rejected: "unclear requirements" -> say which decision is needed and the two options. "not enough context" -> say which file/input you tried to read.
- need names a specific unblock. Rejected: "more information" -> ask one specific question. "human approval" -> state the exact choice.
- Open questions go to beads, never only prose (anti-drift). If your output
raises a question a HUMAN must answer — or you proceeded past one on an
assumption — you MUST capture it as a beads
open-decisionissue (see thegreat-pmskill "Open decisions" section), with the default-if-unanswered and what it blocks. A DONE verdict that buries an unanswered human-decision in prose is rejected: a reader scrolling past the doc loses the question. If you proceeded on a default, name it: "proceeded on assumption X because decision is open." This applies even to DONE — DONE can carry open decisions, as long as they are filed, not buried.
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.
- 1mo ago First seen · 101 lines · 54 tokens per session scan A 0524ba59faaa
done-blocked is a skill published in the GitHub repository VandanaAjayDubey111/great-pm (3 stars, last pushed 1mo ago), licensed MIT. It adds 54 tokens to every session and 1,177 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-09-21.
Other skills, from other repositories
caixun-work-hours
A work-hours reporting assistant for RichPMS, a project time-tracking system. It turns conversation details, code records, or your description into a daily report, lets you confirm it, and then saves or submits it.
commonly
You are a member of a Commonly workspace — a shared space where humans and AI agents from any origin collaborate in pods (chat rooms with memory). Use this whenever you are connected to Commonly via the commonly MCP tools: to read what's happening, post, remember things across sessions, react, DM other agents, and…
nexus-configuration
A skill for reading, planning, approving, and checking configuration in Nexus, the current private conversation or room. It covers settings such as agents, rooms, providers, channels, connectors, skills, models, tools, and MCP connections.
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, UI mockups, product shots, or transparent-background cutouts. Use when the result should be an image asset rather than repo-native SVG, HTML/CSS, or canvas.
sherpa
Guiding workflows by decomposing complex tasks (Epics) into Atomic Steps under 15 minutes each, with progress tracking and drift prevention. Use when complex decomposition is needed.
pm-planning
Decomposition methodology for pm agent — turns an approved ARCH document into a Beads task list with explicit dependencies, time-boxes, and acceptance criteria. The pipeline can only orchestrate work it can see; this skill defines what "seeable work" looks like.