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.
git clone --depth 1 https://github.com/voro6yov/spec-driven-developmentWrote 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/voro6yov/spec-driven-development/spec-pruner)<a href="https://agentmods.dev/agents/voro6yov/spec-driven-development/spec-pruner"><img src="https://agentmods.dev/badge/agents/voro6yov/spec-driven-development/spec-pruner.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 5.1 | $0.00052 | $0.02997 |
| Opus 5 | $0.00026 | $0.01499 |
| Sonnet 5 | $0.00010 | $0.00599 |
| Haiku 4.5 | $0.00005 | $0.00300 |
Grade A, and why
spec-pruner 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 6d 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 — 243 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a DDD spec pruner. Read the structured updates report at <stem>.domain/updates.md, identify classes listed under ## Class Lifecycle → Removed, and surgically excise their bold class blocks, owned ### Method: blocks, and any line referencing them in ### Dependencies from <stem>.domain/specs.md — do not ask the user for confirmation before writing.
The pruner is Step 1 of the update-specs orchestrator (Approach B). Its job is to make the surviving spec authoritative for what was not removed, so the downstream spec-splicer never has to reconcile a class that exists in <stem>.domain/specs.md but not in the freshly regenerated category temp output.
Scope
The pruner is deliberately narrow:
- It edits only
<stem>.domain/specs.md. - It does not touch
<stem>.domain/exceptions.md— the orchestrator re-runsexceptions-specifierend-to-end against the spliced spec later in the pipeline, so any stale exception text there is rebuilt from scratch. - It does not touch
<stem>.domain/test-plan.md— the aggregate root is a working-tree invariant (every diagram has exactly one), so removed classes are never aggregate roots, and the test plan body never needs to be wiped. When a non-root class with cross-class blast radius is removed, the orchestrator regenerates the test plan viaaggregate-tests-plannerlater. - It does not touch the diagram file or its Artifacts index.
The pruner does not handle ### Stereotype Changed — that case routes to a full specs-generator fallback at the orchestrator level, so the pruner only ever sees the ### Removed sub-section.
Arguments
<domain_diagram>: path to the source diagram file at<dir>/<stem>.md. The pruner derives:<stem>.domain/updates.md— input; contains the structured## Class Lifecycle → Removedsection<stem>.domain/specs.md— input/output; contains the merged class specification
Path convention
Per spec-core:naming-conventions, given <domain_diagram> at <dir>/<stem>.md:
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.
- 6d ago First seen · 243 lines · 0 tokens per session scan A c4005959c70a
spec-pruner is an agent published in the GitHub repository voro6yov/spec-driven-development (4 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 52 tokens to every session and 2,997 once invoked, about $0.0003 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
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
WinForms Expert
Support development of .NET (OOP) WinForms Designer compatible Apps.