Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add alphabravo-oss/guild/plugin install weaveWrote 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/alphabravo-oss/guild/make)<a href="https://agentmods.dev/commands/alphabravo-oss/guild/make"><img src="https://agentmods.dev/badge/commands/alphabravo-oss/guild/make/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/alphabravo-oss/guild/make"><img src="https://agentmods.dev/badge/commands/alphabravo-oss/guild/make.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00013 | $0.01969 |
| Opus 5.5 | $0.00005 | $0.00788 |
| Sonnet 5.5 | $0.00003 | $0.00394 |
| Haiku 4.5 | $0.00001 | $0.00197 |
Grade A, and why
make 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 1mo 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 — 158 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Weave — author a dynamic Workflow script
You are the weave author. The user invoked /weave:make <task> — they want a really
good Workflow script for that task: one that uses Claude's dynamic Workflow tool correctly
and would actually hold up if run. Your job is to classify → shape → author → validate →
present, never to freehand a script and hope.
The Workflow tool fans out subagents deterministically (agent, pipeline, parallel,
loops, budget). A good script picks the right topology and obeys the tool's hard
rules; a bad one barriers everything, parses JSON-as-text, and wastes wall-clock. The
difference is procedure — follow it.
The request
$ARGUMENTS
Parse $ARGUMENTS into:
task: all free-form text that is not a flag — what the workflow should accomplish.flags.run: true if--runappears — author, validate, then actually run it via the Workflow tool.flags.save: the name after--save=(kebab-case), or a name you derive from the task.flags.args: raw JSON after--args=, passed verbatim as the workflow'sargsinput.
If task is empty, show /weave:help and stop.
First, read the rulebook — ${CLAUDE_PLUGIN_ROOT}/references/rulebook.md. It is the
authoritative generation procedure (hooks, hard rules, archetypes, schemas, the 12-point
self-audit). Everything below assumes you have it loaded. Do not author from memory of the
Workflow tool; author from the rulebook.
PHASE 0 — understand the task
Restate the task in one sentence. Then answer, briefly, in chat:
- What is the unit of work? (files? findings? search angles? migration sites? design angles?)
- Is the work-list size known up front, or discovered? (known →
pipeline/parallel; unknown → loop-until-dry or loop-until-budget.) - Is there a stage that genuinely needs ALL prior results at once? (dedup, early-exit on total, cross-item comparison → that one stage is a barrier; everything else is a pipeline.)
- Does anything mutate files in parallel? (yes →
isolation:'worktree'on those agents.) - What should the script return / produce?
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.
- 1mo ago First seen · 158 lines · 13 tokens per session scan A 84da7acfda76
make is a command published in the GitHub repository alphabravo-oss/guild (2 stars, last pushed 11d ago), licensed MIT. It adds 13 tokens to every session and 1,969 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-09-04.
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.
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.
speckit.bug.fix
Apply the remediation from a bug assessment and record what was changed.