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/statusgit 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 | $0.00026 | $0.01101 |
| Opus 5 | $0.00013 | $0.00550 |
| Sonnet 5 | $0.00005 | $0.00220 |
| Haiku 4.5 | $0.00003 | $0.00110 |
Grade A, and why
status 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 — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/guild:status — lifecycle helper (read-only)
Reads the active run state: current run, furthest phase, next gate, and blockers. No phase — acts on the active run. Read-only R, writes no file.
Also surfaces the per-phase active team (resolved via
resolveTeamFile(root, slug, null) — consults .current then legacy;
reports "none for this phase" if absent).
Args & local flags
- Args: — (no positional)
--no-index— per-invocation bypass of the optional read-through cache, forcing a one-shot filesystem scan (Invariant FS-CANONICAL: the filesystem stays canonical; the index is never authoritative and never required).
Gates
None — R (read-only).
Output
Prints state (no file written).
Run-start preflight (settings-control-and-tmux U3/U6)
At the very top — before any filesystem scan and before the lightweight
run-trace — the run-trace CLI runs this preflight for you; you do not call
runStartPreflight yourself.
Since wave 2 the run-trace CLI is the sole caller of runStartPreflight
(scripts/lib/runstart-preflight.ts; canonical contract in
guild.md §Run-start preflight): it resolves the 7-source inheritance chain,
validates closed keys, probes tmux, and detects providers. status uses the
lightweight run-trace path (start-and-close at once), so the resolved snapshot
is not persisted for lightweight runs — but the tmux/provider resolution stays
consistent with other commands. Read any resolved config for an existing run
with readResolvedSettingsSnapshot(runId, { cwd }).
Run recording
At the very top of the command body — before any filesystem scan — record a lightweight status run (SC-B OQ6, §435):
node ${GUILD_PLUGIN_ROOT:-${CLAUDE_PLUGIN_ROOT:-$HOME/.local/share/guild/dist/claude-code}}/hooks/dist/run-trace.js status \
--cwd "$(pwd)"
This uses the dedicated status sub-command of run-trace.js, which calls
recordStatusLightweight. Gate: if settings.json record_status_runs: false,
the call is a no-op (pure-read path restored). On the recorded path, writes
only run.yaml + provenance.json to .guild/runs/ — never touches
wiki/decisions/indexes/initiatives. The "status is read-only" contract is
preserved; only a lightweight replay trace is added. No --initiative flag;
no --run-class flag (the status sub-command forces lightweight
internally via B3).
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 · 103 lines · 26 tokens per session scan A 5841bc2754be
status is a command published in the GitHub repository lookatitude/guild (7 stars, last pushed 2d ago), licensed MIT. It adds 26 tokens to every session and 1,101 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 2026-08-31.
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.