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-codenpx skills add voro6yov/spec-driven-development --skill update-codegit 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 | $0.00048 | $0.01324 |
| Opus 5 | $0.00024 | $0.00662 |
| Sonnet 5 | $0.00010 | $0.00265 |
| Haiku 4.5 | $0.00005 | $0.00132 |
Grade A, and why
update-code 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 yesterday.
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 — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the application-layer code updater. After /update-specs has refreshed <stem>.application/updates.md and <stem>.application/ops-updates.md, this skill propagates those deltas into the application package source via gather → implement → review.
This skill is independently invocable (/application-spec:update-code <diagram> [--review]) and is run as part of Wave 2 of /spec-core:update-code (in parallel with persistence). It reads settled domain source; it edits only the application package; it never invokes another plugin.
The two-axis rule — the application layer is a no-op only when both the commands/queries axis (updates.md) and the ops axis (ops-updates.md) are empty — lives entirely inside @application-spec:code-brief-writer, which reads both reports. This skill does not parse either body; it only checks whether the brief-writer produced a brief.
Inputs & outputs
- Reads
<dir>/<stem>.application/updates.md(preflight). Resolves locations via@spec-core:target-locations-finder application. The agents own every other read, including the optionalops-updates.md. - The agents write the durable artifacts:
code-brief.md(Phase 1),code-changes.md+ source edits (Phase 2),code-review.md(Phase 3).
Workflow
Step 0 — Parse arguments
$ARGUMENTS carries <domain_diagram> [--review]. Set RUN_REVIEW=true iff --review is present anywhere; strip it and bind $DIAGRAM to the remaining positional. If none remains:
ERROR: /application-spec:update-code requires <domain_diagram>. Usage: /application-spec:update-code <domain_diagram> [--review]
Step 1 — Preflight
Derive <stem>/<dir> per spec-core:naming-conventions. Read <dir>/<stem>.application/updates.md. If missing, hard-fail:
ERROR: <stem>.application/updates.md not found. Run `/update-specs <domain_diagram>` before `/update-code`.
(The ops-axis report <stem>.application/ops-updates.md is optional — its presence/absence is the brief-writer's concern, not a preflight gate here.)
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.
- yesterday First seen · 94 lines · 48 tokens per session scan A 60836fdaed44
update-code 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 1,324 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.
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…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
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…