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 nicolasmelo1/software-factory --skill factory-evidencegit clone --depth 1 https://github.com/nicolasmelo1/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/nicolasmelo1/software-factory/factory-evidence)<a href="https://agentmods.dev/skills/nicolasmelo1/software-factory/factory-evidence"><img src="https://agentmods.dev/badge/skills/nicolasmelo1/software-factory/factory-evidence/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/nicolasmelo1/software-factory/factory-evidence"><img src="https://agentmods.dev/badge/skills/nicolasmelo1/software-factory/factory-evidence.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00059 | $0.01167 |
| Opus 5 | $0.00030 | $0.00583 |
| Sonnet 5 | $0.00012 | $0.00233 |
| Haiku 4.5 | $0.00006 | $0.00117 |
Grade A, and why
factory-evidence 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 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.
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 — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.
factory-evidence
A feature needs proof. Your job is to make its gate green by proving the thing, never by making a manifest say so.
First decide which state you are in:
- A runnable harness exists: re-run it, collect fresh observations and seal its evidence.
- The feature has no harness or gate: discover the customer flow, write the harness and gate, run the first proof, then seal it.
sf re-reads the raw report, recomputes its digest, and re-checks every
required assertion. Nothing you write in the manifest survives contact with a
report that does not back it.
When the harness does not exist yet
Read the repository before asking questions. Find its README, local-development
commands, service manifests, seed data, test helpers, health endpoints and any
existing end-to-end tests. Run its doctor or readiness command when one exists.
Do not infer that npm test or cargo test starts the product: tests are not a
customer flow.
Settle only the facts code cannot reveal with the maintainer:
- Which actor meets this flow, and what outcome can that actor observe?
- What exact command starts the real entry point, and what dependencies, credentials or seed state does it require?
- What are the smallest observable assertions that make the outcome true?
- How can the harness create and clean up test data without borrowing an internal shortcut the actor would not have?
If an answer is missing, stop and record the prerequisite. A harness that guesses a startup command is a runbook pretending to be a proof.
Create .software-factory/evidence/<gate>-scenario.sh (or the repository's
equivalent executable location). It accepts explicit inputs, starts the real
entry point, waits for readiness, drives the public interface, collects the
observations, and cleans up processes and data even when interrupted. Shell is
a good default for orchestration; use the repository's normal language when
the observations need its client libraries. Do not add a browser driver, a new
test framework or a mock simply to make this easier.
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 Changed · +47 lines · -2 tokens per session 41f207ebf6c1
- 9d ago First seen · 63 lines · 61 tokens per session scan A e52e52795c4b
factory-evidence is a skill published in the GitHub repository nicolasmelo1/software-factory (31 stars, last pushed today), licensed MIT. It adds 59 tokens to every session and 1,167 once invoked, about $0.0003 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 2026-08-30.
Other skills, from other repositories
recipe-create-meet-space
Create a Google Meet meeting space and share the join link.
workthreads
SpecStory Workthreads - a weekly work-thread rollup across a team's repos from SpecStory coding histories (any agent - Claude Code, Codex, Cursor, Gemini, and more). It groups the window's sessions into threads of work per project and labels each new / open / recently closed, so a lead sees what shipped, what is still…
atmos-config
Atmos root configuration: atmos.yaml discovery, precedence, deep merging, basepath, imports, minimal bootstrap, and routing to narrower Atmos skills.
story-readiness
Validate that a story file is implementation-ready. Checks for embedded GDD requirements, ADR references, engine notes, clear acceptance criteria, and no open design questions. Produces READY / NEEDS WORK / BLOCKED verdict with specific gaps. Use when user says 'is this story ready', 'can I start on this story', 'is…
autotask-creator
Rules for automation CRUD from the group-chat commander. The commander does not call mutation tools and does not edit cloud/autotasks files directly. It emits one or more top-level ... containers in its final text; the bus parses and applies them after the turn.
projects
List all managed projects with status, branch, open PRs, and open issue counts — portfolio-level view.