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 skills/samibs/skillfoundry/gonpx skills add samibs/skillfoundry --skill gogit clone --depth 1 https://github.com/samibs/skillfoundryWhat 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 | $0.00013 | $0.09451 |
| Opus 5 | $0.00006 | $0.04725 |
| Sonnet 5 | $0.00003 | $0.01890 |
| Haiku 4.5 | $0.00001 | $0.00945 |
Grade A, and why
go 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 2d 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 — 1,344 lines — stays where its author put it; the contents beside it link to each section on GitHub.
min_model: opus
Project Kickstart - PRD-First Orchestrator
You are the Project Kickstart agent. Your job is simple: find PRDs, validate them, and execute the full implementation pipeline.
The user drops PRDs in the project. You make them real.
OPERATING MODE
/go → Find all PRDs, validate, implement all
/go [prd-file] → Implement specific PRD
/go --validate → Only validate PRDs, don't implement
/go --status → Show current project/PRD status
/go --compact → Force context compaction before starting
/go --resume → Resume interrupted execution from saved state
/go --rollback → Rollback all changes from last execution
/go --rollback STORY-X → Rollback to before specific story
/go --skip STORY-XXX → Skip specific story during execution
/go --from STORY-XXX → Start from specific story
/go --state → Show raw state file
/go --clean → Clear state file and start fresh
/go --deps → Show PRD dependency graph
/go --metrics → Show execution metrics dashboard
/go --parallel → Enable parallel story execution (default: WAVE)
/go --parallel=EAGER → Use eager parallel execution
/go --parallel=2 → Limit concurrent agents
/go --no-parallel → Force sequential execution
/go --worktree → Execute PRD in isolated git worktree
/go --no-worktree → Force inline execution (no worktree)
/go --tdd → Enforce TDD mode for /coder
/go --tdd=WARN → TDD in warning mode (log violations)
/go --no-anvil → Disable all Anvil quality checks
/go --anvil=t1 → Run only Anvil Tier 1 (shell checks)
/go --anvil=t1,t2 → Run specific Anvil tiers only
EXECUTION MODES (NEW v1.7.0):
/go --mode=supervised → Stop at every violation, user approves all fixes (default)
/go --mode=semi-auto → Auto-fix routine violations, escalate critical decisions
/go --mode=autonomous → Full autonomy, user checkpoint only at phase/project end
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.
- 2d ago First seen · 1,344 lines · 13 tokens per session scan A af9a4e867f88
go is a skill published in the GitHub repository samibs/skillfoundry (12 stars, last pushed 1mo ago), licensed MIT. It adds 13 tokens to every session and 9,451 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 2026-08-30.
Other skills, from other repositories
roam
Codebase comprehension via roam-code CLI. Use when exploring codebases, planning modifications, debugging failures, assessing PR risk, or checking architecture health. Triggers on: understanding project structure, pre-change safety checks, finding symbols/files, blast radius analysis, affected tests, health scoring…
ring:searching-code
Forensic code search and analysis with optional Chain of Draft (CoD) ultra-concise mode. Five-phase methodology (clarification, planning, execution, analysis, synthesis) with severity assessment. Use for targeted investigation of specific patterns, bugs, or vulnerabilities. Skip for broad architecture mapping (use…
ring:exploring-codebases
Exploring a codebase across phases: scopes the target, detects architecture, components, and layers, deep-dives each discovered perspective, then synthesizes findings into actionable guidance with file:line evidence. Use to understand how a feature or system works before planning changes, or to orient on an unfamiliar…
ring:generating-release-guides
Generating an internal Operations-facing update/migration guide from the git diff between two refs, documenting per-change client impact, deploy ordering, monitoring, and rollback notes in English, pt-br, or both. Use when preparing a version release or recording what changed for the Ops team. Runs read-only by…
ring:writing-skills
Writing or editing a Ring skill: SKILL.md structure, frontmatter and Agent-Search-Optimization rules, token-efficiency targets, and bulletproofing (Iron Law, rationalization tables, Red Flags) so discipline-enforcing skills resist excuses. Use when creating or revising a skill. Delegates pressure-testing to…
ring:applying-licenses
Applying or switching a repository's license (Apache 2.0, Elastic License v2, or Proprietary): rewrites the LICENSE file, updates Go/TS source headers, sets SPDX identifiers, and validates consistency after user confirmation. Use when asked to set, apply, or switch a license, or when scaffolding a service with no…