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/qagit 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 | $0.00105 | $0.02284 |
| Opus 5 | $0.00053 | $0.01142 |
| Sonnet 5 | $0.00021 | $0.00457 |
| Haiku 4.5 | $0.00011 | $0.00228 |
Grade A, and why
qa 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 — 189 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/guild:qa — phase: Quality [v2]
The Quality phase entrypoint — the full guild:quality skill [v2]
(promoted from the v1 gap-report-only verify-done extension). It
auto-selects the E2E/smoke/a11y/perf/integration class matrix from
CodebaseMap + plan signals (the matrix is surfaced before execution as
[proceed] / [edit-selection] / [explain-signals], overridable, never
silent — there is no --classes= flag) and executes the discovered
harnesses under the run sandbox + budgets. Producer qa-test-strategy vs
security+architect G-quality challenger. Opt-in phase — never
auto-entered, never silently skipped (command-surface.md §6 edge-label
caveat).
This is the Quality phase entrypoint [v2]. Verb↔phase edge:
/guild:qa → Quality. 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 Quality result is the frozen
guild.quality.v1 contract. Quality budgets are consumed from
defaults.quality.budget (set in .guild/settings.json; P1-config-001).
Usage
/guild:qa
/guild:qa run-2026-05-18-ab12
All five global flags + --dry-run apply.
Args & local flags
- Args:
[run-id] - Local flags: — (no
--classes=flag; selection is surfaced + overridable)
Gates (default)
- Release / blocker gate I (a BLOCK→release override is not a soft
gate — it stays human-gated even under
--auto-approve=all) - G-quality review A
Output artifact
.guild/runs/<run-id>/quality/<run-id>.md (frozen guild.quality.v1),
quality/evidence/* (per-class harness output), review/quality/*
(G-quality broker trail).
PCR-Quality must-exist floor: .guild/runs/<run-id>/quality/<run-id>.md,
quality/evidence/*, review/quality/*. Binding:
docs/v2/lifecycle.html §Host-portable phase contract. Ref: DRIFT-ANALYSIS
CMD-011.
Run-start preflight (settings-control-and-tmux U3/U6)
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 · 189 lines · 105 tokens per session scan A c7ce52e8f738
qa is a command published in the GitHub repository lookatitude/guild (7 stars, last pushed 2d ago), licensed MIT. It adds 105 tokens to every session and 2,284 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.