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 Kripu77/software-factory --skill leadgit clone --depth 1 https://github.com/Kripu77/software-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/skills/kripu77/software-factory/lead)<a href="https://agentmods.dev/skills/kripu77/software-factory/lead"><img src="https://agentmods.dev/badge/skills/kripu77/software-factory/lead/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/kripu77/software-factory/lead"><img src="https://agentmods.dev/badge/skills/kripu77/software-factory/lead.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 | $0.00027 | $0.00160 |
| Opus 5 | $0.00014 | $0.00080 |
| Sonnet 5 | $0.00005 | $0.00032 |
| Haiku 4.5 | $0.00003 | $0.00016 |
Grade A, and why
lead 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.
What it actually says
Factory lead
Read lanes/tech-lead.md and AGENTS.md. Follow factory-to-tickets. Ask Telemetry when production data exists. Do not implement. Do not merge.
At the start, run factory.sh mem read for the issue, or for the project if there is no issue. Empty memory is fine. GitHub is the source of truth when local memory has no rows.
After tickets exist, start factory.sh floor, or one factory.sh lane. Dispatch through factory.sh only. Do not implement, review, or watch CI in the lead session.
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 · 13 lines · 0 tokens per session scan A 3f06253f1915
lead is a skill published in the GitHub repository Kripu77/software-factory (6 stars, last pushed 3d ago), licensed MIT. It adds 27 tokens to every session and 160 once invoked, about $0.0001 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 2026-09-06.
Other skills, from other repositories
link-ticket-to-session
Link the current Claude Code session to a ticket (Linear, Jira, GitHub Issues, or GitHub Pull Requests) and cache its title/status in karma. Use when the user explicitly asks to link, attach, associate, or connect this session to a ticket, issue, or PR — e.g. "/link-ticket-to-session ABC-123", "link this session to…
vibe-plan
Use when you have a spec, feature request, or set of requirements that needs to be broken into vibe-kanban issues - decomposes the spec into an issue tree with dependencies, assigns priorities and tier estimates, creates all issues in the project. Pass --local to write the plan to .vibe-flow/plan-local.json instead of…
vibe-ship
Use when you have vibe-kanban issues ready to dispatch to coding agents - turns an issue tree into execution waves with parallel dispatch, executor routing by complexity (T0-T4), and barrier sync between waves.
vibe-status
Use when you want a snapshot of all active vibe-kanban workspaces, their PRs, and any inconsistencies - shows dashboard-style table with workspace state, branch, PR status, CI, and review state, flags anything stuck or inconsistent.
vibe-export-kanban
Use after the final vibe-ship-fast PR has merged to sync results back to vibe-kanban - posts a comment with the PR url and commit SHA on each linked issue, then transitions the issue to done. Idempotent via a marker comment, never modifies title or description.
vibe-import-kanban
Use when you want to ship existing vibe-kanban issues locally with vibe-ship-fast - pulls issues from a vibe-kanban project via MCP and writes them to .vibe-flow/plan-local.json with kanbanid/simpleid preserved, so vibe-export-kanban can sync results back after merge.