spec-recalibrate

spec-recalibrate is a skill for Claude Code from jamesyang124/agent-skills. It costs 108 tokens per session (3,214 once invoked), scanned A, original, MIT.

A local tool that compares written software specifications with the code they describe. It finds differences and, with consent, updates specification documents to match the current code.

In plain words
What is it for?
Use it to review spec-kit or OpenSpec documents across a repository and bring stale specs up to date.
Why use it?
Specifications can become outdated after implementation changes, which can mislead developers. This tool records the drift and changes documentation only, leaving the code untouched.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: mentions subagents; mentions Claude Code.

Good fit Use it to review spec-kit or OpenSpec documents across a repository and bring stale specs up to date.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/jamesyang124/agent-skills/spec-recalibrate
Install

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.

Any agent
npx skills add jamesyang124/agent-skills --skill spec-recalibrate
Clone the repo
git clone --depth 1 https://github.com/jamesyang124/agent-skills

Made for: Claude Code.

Wrote 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.

agentmods badge for spec-recalibrate

README.md
[![agentmods](https://agentmods.dev/badge/skills/jamesyang124/agent-skills/spec-recalibrate/github.svg)](https://agentmods.dev/skills/jamesyang124/agent-skills/spec-recalibrate)
Your own site
<a href="https://agentmods.dev/skills/jamesyang124/agent-skills/spec-recalibrate"><img src="https://agentmods.dev/badge/skills/jamesyang124/agent-skills/spec-recalibrate/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for spec-recalibrate

Your own site · 80×15
<a href="https://agentmods.dev/skills/jamesyang124/agent-skills/spec-recalibrate"><img src="https://agentmods.dev/badge/skills/jamesyang124/agent-skills/spec-recalibrate.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 108 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,214 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00108 $0.03214
Opus 5 $0.00054 $0.01607
Sonnet 5 $0.00022 $0.00643
Haiku 4.5 $0.00011 $0.00321

Measured 12d ago against content hash fd0f89c6b2e0, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

spec-recalibrate 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 12d 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.

.agent-settings/skills/tools/spec-recalibrate/SKILL.md · 110 lines

How it starts

The opening of the file, as written. The whole thing — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Recalibrate Specs Against Code

Keeps spec-driven docs honest over time. Where ado-open-pr Step 1.5 checks one PR's diff against that change's docs just before the PR, this sweeps every existing source-of-truth spec in the repo and re-checks it against the code as it stands now. The code is the source of truth — a spec that disagrees with the code it describes is the stale thing (people forget to sync docs after the last edits), so drifted specs are updated to match the code, with per-spec consent and a versioned history.

This skill is local-only — no Azure DevOps or MCP dependency; it only reads code and writes spec docs on the local filesystem. It's a maintenance companion to the ado-* PR skills: hand the recalibrated specs to ado-open-pr to commit and ship them.

Doc-only invariant — the one rule this skill cannot break. Every write it makes lands in a spec doc (spec-kit specs/…) or an openspec change proposal — nowhere else. It reads code (Glob / Grep / Read) to check specs against it, but it never edits, creates, deletes, or stages a source file. A wrong-looking implementation is a SUSPECT finding for a human (Step 3), never something this skill fixes. If any step would touch a path outside the spec-doc roots enumerated in Step 1, stop and report — that is a bug in the run, not an action to take.

Dependencies

  • An SDD layout in the repo: spec-kit (.specify/ + specs/) or openspec (openspec/). No layout → nothing to calibrate.
  • Optional: .agent-settings/project-config.md (## SDD Tool) to pin the tool without detection.

This skill lives at .agent-settings/skills/tools/spec-recalibrate/ and is auto-discovered by import-skills.sh — no manual copy or registry edit is needed.

Arguments

All optional.

Token / flag Meaning
a path or glob (e.g. specs/001-auth, openspec/specs/billing) calibrate only matching spec(s); default is all specs (full sweep)
--changed-since <ref> narrow to specs whose implementing code changed since a git ref (e.g. main)
--report-only detect and report drift; make no edits
--yes apply DRIFTED-claim fixes without per-spec prompts (never applies SUSPECT / UNVERIFIABLE — see Step 3)
--direct openspec only: hand-edit openspec/specs/ directly instead of emitting a change proposal — bypasses openspec governance; use knowingly

Read the full file on GitHub · 110 lines

Changes

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.

  1. 12d ago First seen · 110 lines · 108 tokens per session scan A fd0f89c6b2e0

Subscribe to this mod's changes

spec-recalibrate is a skill published in the GitHub repository jamesyang124/agent-skills (2 stars, last pushed 1mo ago), licensed MIT. It adds 108 tokens to every session and 3,214 once invoked, about $0.0005 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.