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-triagegit 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-triage)<a href="https://agentmods.dev/skills/nicolasmelo1/software-factory/factory-triage"><img src="https://agentmods.dev/badge/skills/nicolasmelo1/software-factory/factory-triage/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-triage"><img src="https://agentmods.dev/badge/skills/nicolasmelo1/software-factory/factory-triage.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 | $0.00054 | $0.00905 |
| Opus 5 | $0.00027 | $0.00452 |
| Sonnet 5 | $0.00011 | $0.00181 |
| Haiku 4.5 | $0.00005 | $0.00090 |
Grade A, and why
factory-triage 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 5d 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 — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.
factory-triage
Read the report first
sf check already prints, for every finding, what the rule requires, why it
exists, and how to fix it. Read that before touching anything. sf explain <RULE> gives the same for one rule.
sf check --format json when you need to work through many findings
programmatically.
Triage order
sf verify failures come first. A rule that no longer fires on its own
mutation means every green run since it broke proved nothing. Fix the rule
until the fixture trips it again. Never adjust the fixture to match a broken
rule — the fixture is the specification.
Then findings, by severity. critical is L2/L3/L5: drift, a weakened
guardrail, an unproven effect, or a rule nothing proves. Those are never style.
L5.NO_INERT_RULE is not a nuisance. It means a rule is switched on and
looking at nothing — it has been passing every run and reading like protection.
Either point it at something or switch it off and write down why in the rules
document. Do not leave it enabled and inert.
One shape of it arrives without anybody editing the policy: a rule carrying a
when that names a dependency version, after somebody moved the pin. The
finding names the range the rule was written for and the version the manifest
declares now. There is nothing to configure — repoint the rule at the version
this repository installs, or delete it along with the version it described.
Editing the manifest back is not a resolution, and neither is dropping the
when, which leaves the rule firing on code that is now right.
The four honest resolutions
- Fix the code. The default. The
fixline tells you the shape. - Fix the rule. If the rule is genuinely wrong — a query that matches
something it should not, a glob that is too broad — change it deliberately,
update its
why, and re-runsf verify. Say in the pull request that the rule changed and why. That is the reviewable act. - Freeze it, if you are adopting the rule today.
sf ratchet --months 6, and say how many violations were frozen and when they come due. This is only honest at adoption time, not as a way to get past a red build. - Say you cannot. Report the finding, explain what it would take. A blocked build is information.
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.
- 5d ago Changed · +8 lines 0b0e1fb24d3a
- 9d ago First seen · 68 lines · 54 tokens per session scan A c513a9ca9898
factory-triage is a skill published in the GitHub repository nicolasmelo1/software-factory (31 stars, last pushed today), licensed MIT. It adds 54 tokens to every session and 905 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
debug-optimize-lcp
Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…
systematic-debugging
Use when debugging a failing test, build error, or runtime issue that isn't immediately obvious. Guides a 4-phase root cause analysis instead of random fix attempts.
diagnose
Trace from a reproduced symptom to the source code that causes it. Pin the specific file and approximate line, rate confidence in the cause and clarity of the fix independently, and always propose a concrete fix.
repro-admin
Reproduce an EmDash admin UI bug. Attach a container, start the demo dev server, drive the admin with agent-browser using the dev-bypass session, and capture the reproduction as screenshots plus a replayable transcript.
log-error-digest
Analyze log files to troubleshoot errors, identify peak error periods, and produce error clustering, frequency statistics, and time distribution reports. Supports JSON, syslog, and Nginx formats with automatic detection. Use when a user uploads a .log file and asks to analyze errors, find patterns, debug issues, or…
byted-util-volcengine-detect-retry
An orchestration workflow for Volcengine Cloud Detect, a service that checks websites or network endpoints from test locations.