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 commands/samibs/skillfoundry/gosmgit 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/commands/samibs/skillfoundry/gosm)<a href="https://agentmods.dev/commands/samibs/skillfoundry/gosm"><img src="https://agentmods.dev/badge/commands/samibs/skillfoundry/gosm.svg" alt="Measured on agentmods" 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 | $0.00000 | $0.00577 |
| Opus 5 | $0.00000 | $0.00289 |
| Sonnet 5 | $0.00000 | $0.00115 |
| Haiku 4.5 | $0.00000 | $0.00058 |
Grade A, and why
gosm 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 yesterday.
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 — 44 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/gosm - Go Semi-Auto Orchestrator
/gosm is a thin alias for /go --mode=semi-auto. It runs the full /go pipeline but auto-fixes routine issues and escalates only critical decisions to you. This is the recommended execution mode.
Persona: See agents/fixer-orchestrator.md for auto-remediation.
Reflection Protocol: See agents/_reflection-protocol.md.
Dispatch
/gosm [args] → /go --mode=semi-auto [args] with full argument passthrough. Every pipeline phase, Anvil gate, batch/context checkpoint, resume, and delivery audit is defined once in /go; /gosm only preselects the mode.
/gosm genesis/auth.md → /go --mode=semi-auto genesis/auth.md
/gosm --parallel → /go --mode=semi-auto --parallel
/gosm --tdd --parallel → /go --mode=semi-auto --tdd --parallel
/gosm --resume → /go --mode=semi-auto --resume
Extra flags: --resume (continue from saved state), --escalation-log (show deferred escalations).
What semi-auto mode adds
The one behavior semi-auto layers over /go: an auto-fix-vs-escalate decision on every gate finding. Deterministic, routine issues are fixed silently; anything needing human judgment is escalated.
| Category | Issue | Action |
|---|---|---|
| Tests | Missing unit tests / coverage < 80% | AUTO-FIX |
| Security | Missing standard headers (CSP, CSRF) | AUTO-FIX |
| Security | Hardcoded secret / auth-authz pattern choice | ESCALATE |
| Code | Dead code, duplication, banned patterns (TODO/FIXME) | AUTO-FIX |
| Docs | Missing API documentation | AUTO-FIX |
| Performance | N+1 query, missing index | AUTO-FIX |
| Performance | Caching strategy | ESCALATE |
| Architecture | Multiple valid approaches | ESCALATE |
| Business | Ambiguous requirement | ESCALATE |
| Database | Schema design choice | ESCALATE |
| API | Breaking change to consumers | ESCALATE |
On escalation, present: story, phase, issue type, context, options with trade-offs, and a recommendation — then wait for input. If the auto-fix rate falls below 70% for a run, recommend switching to /go (supervised) — most findings need human decisions, so semi-auto is buying little. Everything else — phases, gates, delivery audit — is /go's behavior unchanged.
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.
- yesterday First seen · 44 lines · 0 tokens per session scan A 382c2a1f3e25
gosm is a command published in the GitHub repository samibs/skillfoundry (12 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 577 tokens. 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 2026-09-03.
Other commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.