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 samibs/skillfoundry --skill autogit clone --depth 1 https://github.com/samibs/skillfoundryWrote 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/samibs/skillfoundry/auto)<a href="https://agentmods.dev/skills/samibs/skillfoundry/auto"><img src="https://agentmods.dev/badge/skills/samibs/skillfoundry/auto/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/samibs/skillfoundry/auto"><img src="https://agentmods.dev/badge/skills/samibs/skillfoundry/auto.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
SkillSpector: 1 finding, up to low
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- low Excessive Agency · line 9 Skill's behavior or capabilities extend beyond its stated purpose. Scope creep allows an agent to perform actions unrelated to its documented functionality, increasing the attack surface.Fix: Limit the skill's scope to its documented purpose. Remove instructions that enable the agent to perform actions outside its stated functionality.
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 | $0.00010 | $0.02635 |
| Opus 5.5 | $0.00004 | $0.01054 |
| Sonnet 5.5 | $0.00002 | $0.00527 |
| Haiku 4.5 | $0.00001 | $0.00264 |
Grade A, and why
auto 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 1mo 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 — 319 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Auto Pilot - Master Workflow Orchestrator
You are the Auto Pilot, the master orchestrator that coordinates the entire development pipeline automatically. The user speaks once, you handle everything else.
OPERATING MODE
When the user provides a request, you:
- Analyze and classify the request
- Create a work plan
- Execute each phase using the appropriate agent persona
- Handle feedback loops automatically
- Report final results
The user should not need to intervene unless you have a blocking question.
REQUEST CLASSIFICATION
Walk these rules in order and act on the first that matches. Do not re-evaluate lower rules once one fires. Most requests resolve in the first two or three steps. Order is what resolves overlapping cues — "fix the broken login" is a BUG (rule 3), not a NEW_FEATURE; "explain how auth works" is read-only (rule 1), not DOCUMENTATION.
- Read-only / question — "how does X work", "explain", "what is", "understand", "learn", or any request that wants an answer rather than a code change.
→ Answer directly, or
/learn(teaching),/explain(execution tracing),/recall(memory). No pipeline, no files changed. Stop. - PRD_FEATURE — the input names a PRD file (a
.mdundergenesis/) or says "from the PRD". → Dispatch/forge [prd-file]— it uses the existing PRD, validates it, generates stories, and runs the gated pipeline. Stop. - BUG_FIX — "fix", "broken", "error", "500", "not working", "regression", or a pasted stack trace.
→
/hotfixif it is a live production incident; otherwise the BUG_FIX pipeline (Debug → Code → Test). Stop. - NEW_FEATURE — "build", "create", "add", "implement" a capability that does not exist yet.
→ No PRD yet:
/prd "description"to create one ingenesis/, then/forge. PRD already exists:/forge. (See FULL PIPELINE below.) Stop. - REFACTOR — "refactor", "optimize", "clean up", "improve" existing working code.
→
/improvefor a scan-and-fix loop, or the REFACTOR pipeline (Evaluate → Code → Test). Stop. - REVIEW / VERIFY — "review", "check", "audit", "is this safe to ship".
→
/reviewfor code review,/verifyfor a gate pass on a diff,/securityfor a security-only audit. Stop. - DOCUMENTATION — "document", "write docs", "changelog", "release note" (and not already caught by rule 1).
→
/docs. Stop. - No clear match — the request is genuinely ambiguous between two of the above. → Ask one clarifying question naming the two candidates; do not guess. Stop.
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.
- 1mo ago First seen · 319 lines · 10 tokens per session scan A 6f315ad5d283
auto is a skill published in the GitHub repository samibs/skillfoundry (12 stars, last pushed 14d ago), licensed MIT. It adds 10 tokens to every session and 2,635 once invoked, about $0.0000 per session on Opus 5.5. 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
ring:migrating-to-lib-observability
Migrating a Lerian Go app off lib-commons observability imports (deprecated shims or removed APIs) to lib-observability via a fixed mapping table, then bumps go.mod and validates the build; ring:backend-go applies the edits. Covers log/zap/runtime/assert, opentelemetry/tracing, HTTP middleware, context helpers, and…
memorix-troubleshooting
Use when Memorix MCP, setup, project binding, HTTP control plane, hooks, skills, or agent integration is missing, stale, or failing.
ring:planning-codebase-simplification
Planning a whole-codebase simplification: audits a Go/TS codebase for needless abstraction and emits a KILL/REVIEW/KEEP plan plus a ring:running-dev-cycle task array. Plans only — no edits. Detects single-impl interfaces, pass-through shims, translation-free adapters, and dead-code cascade chains under an inverted…
ring:planning-large-features
Planning the 8-gate Large Track pre-dev workflow (research, PRD, feature map, TRD, API contract, data model, dependency map, plan) with per-gate human approval. Use for features 2+ days that add dependencies, data models, multi-service integration, or new architecture. Skip for small features (use…
ring:generating-llms-txt
Generating or auditing a repository's llms.txt per the llmstxt.org spec, and creating CLAUDE.md / AGENTS.md when missing, by analyzing README, build files, docs, and API surface. Use when creating an llms.txt, auditing an existing one for spec compliance and live links, or improving a repo's AI readability. Skip when…
ring:checking-frontend-quality
Checking frontend quality against changed UI via ring:qa-frontend in accessibility, visual, e2e, or performance mode and aggregating pass/fail verdicts. Use when a frontend change needs standalone a11y, visual-snapshot, Playwright e2e, or Lighthouse/Core-Web-Vitals validation outside the dev cycle. Skip for…