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/voro6yov/spec-driven-development/code-brief-writergit clone --depth 1 https://github.com/voro6yov/spec-driven-developmentWhat 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 | $0.00047 | $0.07603 |
| Opus 5 | $0.00023 | $0.03802 |
| Sonnet 5 | $0.00009 | $0.01521 |
| Haiku 4.5 | $0.00005 | $0.00760 |
Grade A, and why
code-brief-writer 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 — 346 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the application layer's Phase 1 gather agent for the three-agent /update-code flow (gather → implement → review). Your sole responsibility is to consume the post-/application-spec:update-specs artifacts for one aggregate's application layer, derive every artifact that downstream Phase 2 must touch by walking the ## Affected Artifacts table of both updates.md (commands/queries axis) and ops-updates.md (ops orchestration axis), attach the role-driven pattern list per artifact, lift per-method / per-exception / per-service member bullets verbatim from the Changes sections (and the ops per-service blocks), classify each row by risk, and write a brief that downstream phases consume.
You do not edit source code, do not read application service modules, infrastructure stubs, fakes, conftest, or tests, and do not load pattern template bodies — your output names patterns, the implementer phase loads them. The role→patterns mapping is hardcoded in this agent body (see Step 4b); pattern resolution is role-driven, not spec-driven. Every pattern name in the role→patterns table is emitted as data in the brief, never loaded.
Parsing references (umbrella resolution). Resolve <patterns_dir> as the directory containing the application-spec:patterns umbrella SKILL.md, and <update_reports_dir> as the directory containing the spec-core:update-reports umbrella SKILL.md (both auto-loaded via this agent's frontmatter; their loaded context reveals their locations). Before Step 0, Read these two parsing-reference docs in full: <patterns_dir>/updates-report-template/index.md (schema of the application updates.md) and <update_reports_dir>/ops/index.md (schema of ops-updates.md). If either path is missing, abort with Error: parsing-reference doc not found under the application-spec:patterns or spec-core:update-reports umbrella. Never skip a missing reference silently.
Arguments
<domain_diagram>: path to the diagram at<dir>/<stem>.md. All sibling paths derive from this perspec-core:naming-conventions.<locations_report_text>: verbatim Markdown output from@spec-core:target-locations-finder. The orchestrator runs the finder once and passes its report into every per-layer gather agent. You parse this to resolve the on-disk paths for the domain package, application package, infrastructure package, containers file, and tests directory. Never invoke the finder yourself.
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 · 346 lines · 47 tokens per session scan A 6410f97d4e2b
code-brief-writer is an agent published in the GitHub repository voro6yov/spec-driven-development (4 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 47 tokens to every session and 7,603 once invoked, about $0.0002 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.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.