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 agents/sabbour/agentweaver/speckit.squad.generategit clone --depth 1 https://github.com/sabbour/agentweaverWrote 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/agents/sabbour/agentweaver/speckit.squad.generate)<a href="https://agentmods.dev/agents/sabbour/agentweaver/speckit.squad.generate"><img src="https://agentmods.dev/badge/agents/sabbour/agentweaver/speckit.squad.generate.svg" alt="Measured on agentmods" 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 | $0.00010 | $0.00699 |
| Opus 5 | $0.00005 | $0.00349 |
| Sonnet 5 | $0.00002 | $0.00140 |
| Haiku 4.5 | $0.00001 | $0.00070 |
Grade A, and why
speckit.squad.generate 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 4d 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 — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Squad Bridge: Generate
Re-read the implementation plan and regenerate Squad agent definitions, capabilities, and routing rules to stay in sync with plan changes. Safe to run repeatedly — existing agents are updated in place; agents no longer supported by the plan are flagged (not deleted).
This command is also triggered by the after_plan hook.
User Input
$ARGUMENTS
Steps
-
Verify
.squad/exists — if not, tell the user to run/speckit.squad.initfirst and stop. -
Read the plan from the active spec directory under
specs/(e.g.,specs/001-<name>/plan.md). Also readspec.mdfor supplementary context (goals, constraints). -
Load bridge config from
.specify/extensions/squad/squad-config.ymlif it exists, otherwise use extension defaults. -
Read existing agents from
.squad/agents/(each agent lives in.squad/agents/{name}/charter.md) so changes can be diffed rather than blindly overwritten. Preservehistory.mdfiles (accumulated project knowledge — never touch these). -
Analyze the plan to extract technology stack, architecture layers, implementation phases, and cross-cutting concerns (same logic as
init). If$ARGUMENTSnames a specific domain, limit regeneration to that domain's agent. -
Diff against existing agents:
- New domains found in plan but no matching agent → create new agent
- Changed domains (different prominence or tech stack) → update agent capabilities and model tier
- Removed domains (in existing agents but absent from new plan) →
set
status: inactiveand note in output (do NOT delete)
-
Update
squad.config.tsat the project root (usingdefineSquad()withdefineTeam(),defineAgent(), anddefineRouting()) to reflect the new agent set, routing rules, and model tier assignments. -
Update
.squad/routing.mdto add routing rules for any new agents and update patterns for changed agents.
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.
- 4d ago First seen · 75 lines · 10 tokens per session scan A 6d654855cf42
speckit.squad.generate is an agent published in the GitHub repository sabbour/agentweaver (5 stars, last pushed today), licensed MIT. It adds 10 tokens to every session and 699 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 agents, from other repositories
AGENTS
Files in this directory. One row per file. Non-source area. Project-tier subagent definitions; resolved by pi-dashboard-subagents tier 1 ( /.pi/agents/ .md), beating user/bundled/package tiers. Frontmatter schema: description, model, thinking, tools, inheritcontext, prompt. tools: MUST be YAML array form …
cli
Use as the primary implementation agent for this .NET repository. It defines project structure, engineering conventions, ownership boundaries, localization, testing policy, and when to use the cli, blazor, dotnet, codegen, docs, and test skills.
merge-scan
Not a prompt: this definition executes a fixed command template via the deterministic command adapter (lib/adapters/command.mjs). No model runs.
merge-apply
This is a closed command definition, not a model prompt. Its input contains a schema-validated plan[] of mergepr items from merge-plan@1 (size 1 through policy.merge.batchsize). Immediately before each squash, the command re-reads that PR's head and base SHA, exact branch names, open/draft/mergeable state, GitHub and…
merge-notify
Not a prompt: this definition executes a fixed command template via the deterministic command adapter (lib/adapters/command.mjs). No model runs.
wpf-control-designer
WPF CustomControl design and implementation specialist. Defines DependencyProperty, implements Parts and States Model, OnApplyTemplate patterns.