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/koldovsky/project-factory/onboardgit clone --depth 1 https://github.com/koldovsky/project-factoryWrote 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/koldovsky/project-factory/onboard)<a href="https://agentmods.dev/commands/koldovsky/project-factory/onboard"><img src="https://agentmods.dev/badge/commands/koldovsky/project-factory/onboard.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 | $0.00046 | $0.01067 |
| Opus 5 | $0.00023 | $0.00534 |
| Sonnet 5 | $0.00009 | $0.00213 |
| Haiku 4.5 | $0.00005 | $0.00107 |
Grade A, and why
onboard 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 3d 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 — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/project-factory:onboard — adopt an existing repo
Bring an existing codebase under spec-driven control without clobbering it.
Onboarding only DOCUMENTS and INSTALLS — it never rewrites existing code. Full
detail: ${CLAUDE_PLUGIN_ROOT}/skills/project-factory/references/existing-project.md.
Steps
-
Detect the stack — read
package.json, framework + version, dir layout, test runner, CI. Record as ADR-0001 (adopt what's there; don't migrate). -
Install the loop (non-destructive merge) — run the
/project-factory:initsteps in merge mode: copy agents/workflows/scripts/hooks/CI/OpenSpec/templates — including the reflection layer (init steps 3, 3b, 8b, 9: acceptance/ visual/process/integrity checks, ledger + digest, correction intake, retro schemas,process-auditoragent, lesson upsert intoAGENTS.md) — wirepackage.jsonscripts, and install the multi-tool adapters (init step 10 —--toolshonored), SKIPPING anything that already exists and merging.claude/settings.json/ CI / hooks rather than replacing. Adaptqa-verify's battery to the scripts the project has. Report added vs skipped.
2b. Pre-seed historical-only waivers (so brownfield is not instantly red). Legacy code has no red-first history, no acceptance artifacts, and no ledger — without waivers the honesty checks would render the whole baseline NOT-EARNED on day one and train the team to ignore red. For each BASELINE-ONLY gap (never for new work):
docs/qa/waivers/<date>-baseline-<req-id>.mdnaming the requirement id and statinghistorical-only: pre-onboarding baseline; evidence cannot be reconstructed(check-acceptance-methods renders these as visible WAIVED lines + counted warnings, not silent passes);- ratchet loosenings, if any legacy baseline must start below current
state, as
docs/qa/waivers/*.json{check, metric(s), reason}. Then runnode scripts/correct.mjs --detect— waiver creation auto-appends correction events by design — and disposition each aswaivedwith notehistorical-only brownfield baseline. The user confirms this waiver set at the baseline sign-off checkpoint (step 4); every waiver stays visible in gate output forever. New slices get ZERO pre-seeded waivers.
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.
- 3d ago First seen · 74 lines · 46 tokens per session scan A 051fbe04e7d5
onboard is a command published in the GitHub repository koldovsky/project-factory (4 stars, last pushed 1mo ago), licensed MIT. It adds 46 tokens to every session and 1,067 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
project-recap
Generate a visual project recap for context switching.
os-meeting
快速创建和管理AI团队会议.
workspace
Testany Workspace, 管理工作空间，成员权限，团队组织.
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-issues
Launch the Issue Triage Agent (Haiku) to categorize and prioritize GitHub issues.