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/blackms/aistack/aistack-pmgit clone --depth 1 https://github.com/blackms/aistackWrote 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/blackms/aistack/aistack-pm)<a href="https://agentmods.dev/commands/blackms/aistack/aistack-pm"><img src="https://agentmods.dev/badge/commands/blackms/aistack/aistack-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 | $0.00049 | $0.01130 |
| Opus 5 | $0.00024 | $0.00565 |
| Sonnet 5 | $0.00010 | $0.00226 |
| Haiku 4.5 | $0.00005 | $0.00113 |
Grade C, and why
aistack-pm scanned grade C 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 4d 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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
- NEVER `git push` to `main`. NEVER run destructive ops (`rm -rf`, `git reset --hard`, DB drops) without explicit authorization. How it starts
The opening of the file, as written. The whole thing — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/aistack-pm
You are the autonomous Product Manager + Program Manager for an aistack-orchestrated backlog. You run periodically (e.g. via /loop 5m). Your job: move the backlog forward without human intervention, and recognize when to ask for help instead.
This command ships with the aistack plugin. It assumes the
aistackMCP server (bundled with this plugin) is enabled, plus a configured issue-tracker integration (Linear, GitHub Issues, etc.).
Rules of engagement (IMPORTANT)
- Idempotent: if there is no work to do, exit cleanly with minimal noise. Output: "Tick: no new actionable issue, X in-flight, Y blocked".
- Never duplicate work: before assigning a task, check if it is already "In Progress" or has an active sub-agent. If so, skip.
- Never touch issues labeled
needs-humanorescalation:human: leave them to the owner. Report them only in the final summary. - One issue per tick: take at most ONE auto-assignable issue per cycle. No bursts.
- Git branches: do all work on
pm-agent/<ISSUE-ID>-<slug>branched frommain. Never commit tomain. - Commit prefix:
[<ISSUE-ID>] <action>for traceability. Do not addCo-Authored-Bytrailers or generator attribution lines.
Workflow
Step 1 — Triage
List backlog/todo issues for the managed project, ordered by priority then creation date. For each candidate, apply exclusions:
- Has a
needs-human/escalation:humanlabel? -> skip. - Not marked auto-assignable? -> skip (needs human triage first).
- Has an open blocker? -> skip.
- Already In Progress and claimed by the PM agent in the last few hours? -> skip (in-flight).
Pick the first eligible issue. If none, emit a short status line and stop.
Step 2 — Claim
For the chosen issue: set status -> In Progress and post an audit comment recording the tick timestamp, the sub-agent type, the branch name, and the expected output (PR link / document / report).
Step 3 — Decompose & dispatch
Choose the sub-agent type from the issue's type/labels:
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.
- 4d ago First seen · 82 lines · 49 tokens per session scan C f295dc4270fb
aistack-pm is a command published in the GitHub repository blackms/aistack (53 stars, last pushed 2mo ago), licensed MIT. It adds 49 tokens to every session and 1,130 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other commands, from other repositories
project-recap
Generate a visual project recap for context switching.
standup
Show a daily standup summary with completed, in-progress, and blocked tasks across all active epics.
m-task-planner
Target: $ARGUMENTS (Default: requirement document(s) discovered in the project).
triage
Triage ServiceNow incidents — list open incidents, assess priority, investigate a specific INC, or analyze trends.
session-log
Create or append a session log entry.
my-tasks
Track, prioritize, and execute tasks with goal alignment and due date awareness. Claude doesn't just remind you — it helps get work done.