guild
01Plugin Claude Code
Plugin marketplace for Guild — the spec engine and the build engine for Claude Code.
2 2d ago A
tokens not measured
original MIT
adhoc
02Plugin Claude Code
Stops Claude from racing on ad-hoc work. Methodical-mode pre-response checklist injected every turn (Restate, Verified/Unverified assumptions, Read Floor, Approach Deliberation, Blast Radius, Stall Check, Competing Hypotheses, Goal-Driven Execution). Stop hook enforces four gates: file:line citation verifier…
2 2d ago A
tokens not measured
original MIT
fast-critic
03Agent
Hook-invoked fast-tier critic for adhoc methodical-mode iterative gate-dialog. Spawned by the Stop hook on rounds 1-2 of a substantive response. Runs a 10-item rule compliance audit using a cheap small-model pass. Returns per-rule pass/fail/N/A plus an overall verdict (CONCUR | CONCUR WITH CAVEATS | PUSH BACK | WRONG…
2 2d ago A 139 tokens
original MIT
Agent
Hook-invoked deep-tier critic for adhoc methodical-mode iterative gate-dialog. Spawned by the Stop hook on rounds 3-5 of a substantive response (escalation tier — the cheap Haiku fast-critic ran rounds 1-2 and either flagged repeated failures or the response is long enough to warrant deep review). Runs the same…
2 2d ago A 183 tokens
original MIT
Agent
Independent fresh-context critique. Spawn this agent when you want a take from a Claude that has NOT seen the conversation — useful for sanity-checking a recommendation, reviewing a plan before execution, or breaking out of a reasoning rut. Pass the full problem statement, the proposed approach, and any constraints in…
2 2d ago A 90 tokens
original MIT
casual
06Command
Skip adhoc methodical-mode for the next single turn (auto-reverts after one prompt).
2 2d ago A 19 tokens
original MIT
Command
Disable the adhoc Stop hook citation verifier.
2 2d ago A 8 tokens
original MIT
citations-on
08Command
Enable the adhoc Stop hook citation verifier (default mode).
2 2d ago A 12 tokens
original MIT
help
09Command
Show the adhoc plugin commands and how the methodical-mode hook works.
2 2d ago A 14 tokens
original MIT
off
10Command
Disable adhoc methodical-mode injection for the rest of this session.
2 2d ago A 13 tokens
original MIT
on
11Command
Re-enable adhoc methodical-mode injection.
2 2d ago A 8 tokens
original MIT
status
12Command
Show the current adhoc methodical-mode and citation-verifier state.
2 2d ago B 13 tokens
original MIT
strict-off
13Command
Disable the adhoc Stop hook strict gates (grounding audit + critic-agent gate).
2 2d ago A 17 tokens
original MIT
strict-on
14Command
Enable the adhoc Stop hook strict gates (grounding audit + critic-agent gate).
2 2d ago A 17 tokens
original MIT
trust-me
15Command
One-shot bypass of adhoc strict gates (grounding + critic) for the next single turn.
2 2d ago A 19 tokens
original MIT
Command
Disable the adhoc Stop hook uncertainty-tell scanner.
2 2d ago A 10 tokens
original MIT
Command
Enable the adhoc Stop hook uncertainty-tell scanner (default mode).
2 2d ago A 14 tokens
original MIT
Hook
Runs when you submit a prompt, before the agent sees it, executing inject.sh. From alphabravo-oss/guild.
2 2d ago A
tokens not measured
copy · 58% MIT
Stop
19Hook
Runs when the agent finishes a response, executing check-citations.py. From alphabravo-oss/guild.
2 2d ago A
tokens not measured
copy · 64% MIT
deep
20Skill Claude CodeCodex
Heavier methodical workflow for ad-hoc tasks where the always-on preamble isn't enough. Forces a structured analysis pass — task framing, hidden-assumption hunt, prior-art check, alternatives with tradeoffs, edge cases, recommendation with stop-points — before any code change. Use when the task is non-trivial…
2 2d ago A 84 tokens
original MIT
crew
21Plugin Claude Code
Throw an AI dev at a problem and have it own the outcome. Five Opus agents (router, scout, worker, critic, fresh-eyes) collaborate to investigate, plan, execute, and verify — SSH into systems, spin up infra, edit code, ship features, debug deploys, get airgap bundles working. Worker self-switches between investigating.
2 2d ago A
tokens not measured
original MIT
critic
22Agent
Crew critic. Adversarial verifier. Reads the original intent, the plan (if any), and the current state of code/systems. Runs real commands to check the work — does NOT read the worker's journal or trust the worker's self-report. Produces a falsifiable pass/fail verdict with an evidence ledger. Orchestrator rejects…
2 2d ago A 79 tokens
original MIT
fresh-eyes
23Agent
Crew fresh-eyes. Blind drift checker. Reads ONLY the original user intent and the current state of the codebase/systems — no brief, no plan, no journal, no critic verdict. Pretends to be a colleague who just walked up and was told what the user wanted. Checks whether the user got what they asked for. Mandatory final…
2 2d ago C 82 tokens
original MIT
router
24Agent
Crew router. Classifies a free-form intent into initial worker mode (investigating | planning | executing), scope (light | deep | paranoid), side-effect surface (none | local | remote | production), and flag interpretation (--paranoid, --yolo). One-shot classifier. Returns a JSON config the orchestrator uses to…
2 2d ago A 73 tokens
original MIT