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 skills add jamesyang124/agent-skills --skill spec-recalibrategit clone --depth 1 https://github.com/jamesyang124/agent-skillsWrote 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/jamesyang124/agent-skills/spec-recalibrate)<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.
<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>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 | $0.00108 | $0.03214 |
| Opus 5 | $0.00054 | $0.01607 |
| Sonnet 5 | $0.00022 | $0.00643 |
| Haiku 4.5 | $0.00011 | $0.00321 |
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.
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 |
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.
- 12d ago First seen · 110 lines · 108 tokens per session scan A fd0f89c6b2e0
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.
Other skills, from other repositories
autoreview
Pre-commit/ship code review: Codex default; optional Claude or Pi.
omh-code-review
This is a Hermes-native code-review workflow skill.
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
code-reviewer
Code review specialist focused on patterns, bugs, security, and performance.
full-repo-review
Comprehensive four-wave review of all repo source files, producing a prioritized issue backlog.
agent-teams-simplify-and-harden
Implementation + audit loop using parallel agent teams with structured simplify, harden, and document passes. Spawns implementation agents to do the work, then audit agents to find complexity, security gaps, and spec deviations, then loops until code compiles cleanly, all tests pass, and auditors find zero issues or…