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 skills/voro6yov/spec-driven-development/update-specsnpx skills add voro6yov/spec-driven-development --skill update-specsgit 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/skills/voro6yov/spec-driven-development/update-specs)<a href="https://agentmods.dev/skills/voro6yov/spec-driven-development/update-specs"><img src="https://agentmods.dev/badge/skills/voro6yov/spec-driven-development/update-specs.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 | $0.00048 | $0.11720 |
| Opus 5 | $0.00024 | $0.05860 |
| Sonnet 5 | $0.00010 | $0.02344 |
| Haiku 4.5 | $0.00005 | $0.01172 |
Grade A, and why
update-specs 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 5d 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 — 426 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are an application spec update orchestrator. Given a domain diagram and its sibling commands/queries application-service diagrams (plus any <dir>/<stem>.ops.<op-name>.md ops orchestration diagrams), refresh the existing <dir>/<stem>.application/commands.specs.md, <dir>/<stem>.application/queries.specs.md, every dirty <dir>/<stem>.application/ops.<op-name>.specs.md, and <dir>/<stem>.application/services.md in place — invoke the three app-service-axis update detectors (commands, queries, ops), re-run only the dirty side's / dirty ops service's writers, re-enrich application exceptions, re-run services-finder, and emit <dir>/<stem>.application/updates.md (plus the ops detector's <dir>/<stem>.application/ops-updates.md). Do not rerun the full @application-spec:specs-generator pipeline, do not touch the diagram files, and do not ask for confirmation before writing.
This is a pure single-plugin updater — it touches only the <stem>.application/ siblings and invokes only application-spec agents. It does not cascade to rest-api or messaging. Cross-layer propagation is owned by /spec-core:update-specs <domain_diagram>, which runs this skill (its application wave) before the rest-api/messaging wave so the three detector reports this skill produces are on disk when those leaves read them. Run /spec-core:update-specs for a full cross-layer update; run this skill directly for an application-only update.
This skill is the application-side counterpart to /update-specs (domain) and /persistence-spec:update-specs. Design rationale lives in notes/spec-updater-approach.md, notes/update-types.md, notes/updates-report.md, notes/commands-queries-detectors-approach.md, notes/commands-queries-update-types.md, notes/commands-queries-updates-report.md, and notes/commands-queries-integration-approach.md; the load-bearing idea is per-side snapshot regen — every section of <side>.specs.md is a pure snapshot, so the surgical unit of work is one full side, not one method block. Commands and queries are independent; a delta on any of the three input axes touches at most one or both.
The orchestrator consumes four update reports — one per axis — and unions their dispatch signals:
- Domain axis —
<dir>/<stem>.domain/updates.md, produced bydomain-spec:updates-detector(consumed if present; absent ⇒ the domain axis is treated as no-change per Step 0a — never invoked or produced here). - Commands-diagram axis —
<dir>/<stem>.application/commands-updates.md, produced byapplication-spec:commands-updates-detector(invoked at Step 0 below). - Queries-diagram axis —
<dir>/<stem>.application/queries-updates.md, produced byapplication-spec:queries-updates-detector(invoked at Step 0 below). - Ops-diagram axis —
<dir>/<stem>.application/ops-updates.md, produced byapplication-spec:ops-updates-detector(invoked at Step 0h below). One aggregate-wide report covering every<dir>/<stem>.ops.<op-name>.md; absent/empty when the aggregate declares no ops services. This skill produces the ops report for its own dispatch; the rest-api / messaging updaters re-invoke the detector themselves (it is outside the--detectors-freshpromise) and fast-path on its digest sentinel.
The orchestrator never re-diffs any diagram itself.
This skill is the single producer of the three app-service-axis detector reports (commands-updates.md, queries-updates.md, ops-updates.md) that the rest-api and messaging updaters consume. It produces them at Step 0 for its own dispatch; the /spec-core:update-specs orchestrator sequences this skill before the rest-api/messaging wave precisely so those reports are on disk (and byte-stable) when the leaves read them under --detectors-fresh. This skill itself never invokes rest-api or messaging — it only produces the reports they depend on. Its behaviour is identical whether invoked standalone (for a commands/queries/ops-diagram change) or as the application wave of /spec-core:update-specs.
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.
- 5d ago First seen · 426 lines · 48 tokens per session scan A 6bc13df2739a
update-specs is a skill published in the GitHub repository voro6yov/spec-driven-development (4 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 48 tokens to every session and 11,720 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 skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…