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/lookatitude/guild/opsgit clone --depth 1 https://github.com/lookatitude/guildWhat 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 | $0.00107 | $0.02275 |
| Opus 5 | $0.00053 | $0.01137 |
| Sonnet 5 | $0.00021 | $0.00455 |
| Haiku 4.5 | $0.00011 | $0.00228 |
Grade A, and why
ops 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 — 190 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/guild:ops — phase: Operations [v2]
The Operations phase entrypoint — the full guild:operations skill
[v2] (promoted from the v1 reserved notice). Five runbook classes —
release / monitoring / incident / rollback / maintenance — selected by the
positional [runbook] else by surfaced detection (always confirmed,
overridable), under a split autonomy posture + four non-negotiable
safety rails: incident/rollback never autonomous; first run always
interactive; the always-ask hard set is unconditional; a pre-flight dry-run
is mandatory. Producer devops-* vs security+architect G-operations
challenger. Consumes Quality, feeds the D8 release leg.
This is the Operations phase entrypoint [v2]. Verb↔phase edge:
/guild:ops → Operations (node id OPS). Phase concept binding:
lifecycle/phase-entrypoints.md · lifecycle/lifecycle-overview.md.
Contract binding
Before producer work begins, this phase resolves the frozen
guild.phase_entry.v1 contract. The Operations record is the frozen
guild.ops.v1 contract (safety_rails included); by class it also writes
guild.incident.v1 and guild.release.v1 (D8 join).
Full contract detail: https://guildstack.dev/docs.
Usage
/guild:ops
/guild:ops release
All five global flags + --dry-run apply. The mandatory pre-flight dry-run
is a safety rail, independent of --dry-run.
Args & local flags
- Args:
[runbook](one of: release / monitoring / incident / rollback / maintenance; else surfaced detection) - Local flags: —
Gates (default)
- Risky / destructive I always (a
release, destructive,incident, orrollbackaction always prompts even under--auto-approve=alland even inside anapproved:trueautonomous runbook) - G-operations review A
Output artifact
.guild/runs/<run-id>/ops/<run-id>.md (frozen guild.ops.v1),
guild.incident.v1 / guild.release.v1 records by class,
review/ops/* (G-operations broker trail).
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 · 190 lines · 107 tokens per session scan A 0f52edc8dec9
ops is a command published in the GitHub repository lookatitude/guild (7 stars, last pushed yesterday), licensed MIT. It adds 107 tokens to every session and 2,275 once invoked, about $0.0005 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 2026-08-31.
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.