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/dormstern/forge/pm-modenpx skills add dormstern/forge --skill pm-modegit clone --depth 1 https://github.com/dormstern/forgeWhat 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 | $0.00084 | $0.01318 |
| Opus 5 | $0.00042 | $0.00659 |
| Sonnet 5 | $0.00017 | $0.00264 |
| Haiku 4.5 | $0.00008 | $0.00132 |
Grade A, and why
pm-mode 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 2d 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 — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PM mode
You ship a living product through repeating release cycles. Each cycle has discipline — kill list, drift checks, autonomy tiers, stabilization triggers.
Difference from Founder mode: Founder mode is finite (3–5 cycles → graduate or kill). PM mode runs forever — every release ships, measures, harvests signals for the next.
The cycle
HARVEST → SHAPE → BUILD → SHIP, then loop.
HARVEST (15–30 min)
Collect raw signals from feedback, analytics, tickets, competitive observations. Auto-mine git log + open issues + recent PRs. Categorize each, assess thesis_impact (null / confirms / challenges / invalidates), refresh architecture.md incrementally.
Pause: review signal summary. Invalidations get prominent flagging.
SHAPE (30–60 min) — the hero phase
Propose a release plan:
- Thesis (1 sentence)
- Identity evolution — only if signals warrant. Trigger + rationale + risk.
- Features — each with
signal_id,requested_by,intent,autonomy(T1/T2/T3) - Debt paydown (~15%)
- Kill list (≥10%) — the 10% Delete Rule. Mandatory.
- Contract implications (if
contract_mode != "none") - Appetite — what's NOT included
- Stabilization check — auto-fire on rework>15% / blocked≥3 / resets>2 / quality<6
Devil's Advocate auto-runs against the plan. Surfaces 2–3 attacks inline. The output is the hero card — screenshottable monospace render with ✓/⚠/✗ markers.
Pause: human approves, modifies, or kills the cycle.
BUILD (async, hours)
Feature breakdown decomposes the plan into a wave (additive — don't re-implement what's done). Then the Ralph Loop:
SELECT next feature → TEST (3–7 acceptance tests) → BUILD (fresh context, max 3 resets) → EVALUATE
Autonomy tiers determine where humans checkpoint:
| Tier | Test | Build | Commit |
|---|---|---|---|
| T1 | Auto | Auto | Auto-commit |
| T2 | Auto | Auto | Checkpoint before commit |
| T3 | Checkpoint | Checkpoint | Checkpoint before commit |
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.
- 2d ago First seen · 100 lines · 84 tokens per session scan A 368f891fed4e
pm-mode is a skill published in the GitHub repository dormstern/forge (6 stars, last pushed 3mo ago), licensed MIT. It adds 84 tokens to every session and 1,318 once invoked, about $0.0004 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 skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
agent-host-chat-contributions
Build and review cross-cutting agent-host chat behavior through lifecycle contributions. Use when adding turn lifecycle side effects, prompt or context injection, restored-history transformation, protocol-action observation, or when reviewing changes that add code to AgentSideEffects or AgentService.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.