A PM-mode command that gathers raw product signals and updates the project's codebase map. Signals can include customer feedback, usage data, support tickets, competitor changes, internal observations and recent code changes.

Use it to collect signals from users and the project, categorize them, check whether they affect the product thesis, flag invalidated assumptions and refresh architecture.md. A release cycle is a planned period of product work.

It turns scattered evidence into a structured record for the next release cycle. It also highlights changes that may challenge the product's current direction and keeps the architecture documentation current.

harvest — Command by dormstern

Install

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.

agentmods

npx agentmods add commands/dormstern/forge/harvest

Clone the repo

git clone --depth 1 https://github.com/dormstern/forge

Per session 39 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 587 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. Scan, not verified.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00039	$0.00587
Opus 5	$0.00019	$0.00293
Sonnet 5	$0.00008	$0.00117
Haiku 4.5	$0.00004	$0.00059

Measured 2d ago against content hash f14f389552c8, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

harvest 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.

commands/harvest.md · 46 lines

How it starts

The opening of the file, as written. The whole thing — 46 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/forge:harvest — Signal harvest + architecture refresh (PM mode)

Execution mode: direct. This command has explicit steps below — execute them in order. Do not enter plan mode, do not write a plan file, do not call ExitPlanMode. The framework already did the planning; you just run the steps.

You start a new release cycle by collecting raw signals and updating the codebase map.

Behavior

Read state. releases.json (signals from last 2 releases for context), features.json (tech_debt items), IDENTITY.md (WHO/JOB/NEVER), architecture.md.
Collect raw signals from the user. Ask once:

"Drop me your raw signals — feedback, analytics, tickets, customer quotes, competitive moves, internal observations, anything from the last cycle. I'll structure them."

Also auto-mine the project: recent commits (last 30), open issues (gh issue list), recent PR descriptions, README changes. These count as signals if they reveal pain or direction shifts.
Structure each signal into the releases.json current_cycle.signals array:
- id: SIG-NNN
- category: user_pain | feature_request | usage_pattern | production_health | tech_debt | competitive | rework
- title, source, quote (verbatim), date
- impact: 1-line estimate
- strength: HIGH | MEDIUM | LOW
- thesis_impact: null | confirms | challenges | invalidates
- requested_by
Flag invalidations prominently. If any thesis_impact = "invalidates", surface it at the top of the report. The user must decide whether to pivot the cycle.
Refresh architecture.md incrementally. Re-scan only changed modules (use git diff since last release tag). Don't regenerate from scratch.
PAUSE — Present the signal summary. Group by strength, then by category. Highlight invalidations and the top 3 highest-strength signals.

Constraints

Every signal must have signal_id, source, and requested_by. No phantom signals.
Quote verbatim. Don't paraphrase.
Phase announcement: print --- PHASE: HARVEST --- at start.

Read the full file on GitHub · 46 lines

Changes

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 · 46 lines · 39 tokens per session scan A f14f389552c8

Subscribe to this mod's changes

harvest is a command published in the GitHub repository dormstern/forge (6 stars, last pushed 3mo ago), licensed MIT. It adds 39 tokens to every session and 587 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.

Analytics and metrics Project management

template

Manage issue templates for streamlined issue creation.

gastownhall/beads · 0 tokens

speckit.auto

Automatically execute the four core phases of the Spec-Driven Development (SDD) pipeline: specify → plan → tasks → implement, in strict sequential order.

VisActor/VChart · 31 tokens

daily-priorities

Query DIGI Jira via the Atlassian MCP to build a prioritized daily work plan. The report has two parts: suggested priorities (the recommendation) and full context (everything you need to evaluate whether the suggestions are right and what else is on the docket).

DIGI-UW/OpenELIS-Global-2 · 0 tokens

harvest