A workflow for keeping a feature's implementation, specification, threat model, API description, and user documentation consistent. A threat model records possible security threats and how the feature addresses them.

Use it when changing a feature that has internal specifications, threat models, API descriptions, or documentation. It compares the documents with the implementation and updates the correct side of each mismatch.

It finds cases where code and its written description disagree, so requirements, APIs, configuration, errors, and security expectations do not become outdated.

How thunder-id/thunderid configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to thunder-id/thunderid. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/thunder-id/thunderid/main/.agent/skills/spec-sync/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/thunder-id/thunderid

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/thunder-id/thunderid/spec-sync/github.svg)](https://agentmods.dev/skills/thunder-id/thunderid/spec-sync)

Your own site

<a href="https://agentmods.dev/skills/thunder-id/thunderid/spec-sync"><img src="https://agentmods.dev/badge/skills/thunder-id/thunderid/spec-sync/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/thunder-id/thunderid/spec-sync"><img src="https://agentmods.dev/badge/skills/thunder-id/thunderid/spec-sync.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 62 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 570 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.

Model	Per session	Once invoked
Fable 5.1	$0.00062	$0.00570
Opus 5.5	$0.00025	$0.00228
Sonnet 5.5	$0.00012	$0.00114
Haiku 4.5	$0.00006	$0.00057

Measured 6d ago against content hash 1851296c80bb, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

spec-sync 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 6d 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/skills/spec-sync/SKILL.md · 49 lines

How it starts

The opening of the file, as written. The whole thing — 49 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Spec Sync

Specifications and threat models describe the feature as built, not only as planned. When the implementation and a document disagree, one of them changes.

Step 1: Find the Documents

The feature's docs-internals/<feature>/spec.md and threat-model.md. The spec's Related documents line links the threat model, issues, and discussions.
User documentation under docs/content/ that describes the behaviour: config tables, API references, error codes, flows.
The API spec in api/*.yaml for any endpoint the change touches.

Step 2: Compare

Check the implementation against the spec for: requirements and acceptance criteria, behaviour and failure handling, API shape and error codes, data model, config keys and defaults, event names, and anything the spec marks as out of scope.

For each mismatch:

If the spec is right, fix the code.
If the implementation is the intended design, update the spec.
If it is unclear which is right, ask before changing either.

Never leave a mismatch unrecorded.

Step 3: Update the Spec

Change the affected section so it describes what is built.
Bump the minor version in the header (0.3 becomes 0.4). For a considerable change to a released feature, breaking or not, bump the major version instead (1.2 becomes 2.0).
Add a row to the Change log table: the new version, today's date, and a one-line change that references the update.
Keep Status as it is.
Requirements and acceptance criteria that moved out of scope go to a future specification, not deleted silently.

| 0.4 | 2026-10-20 | Retries stop after the configured attempt limit, as implemented in #5700. |

Step 4: Update the Threat Model

Update threat-model.md when the change alters a trust boundary, an actor's entitlements, an interaction, or a mitigation the model relies on. Bump its minor version and add a change log row the same way.

Step 5: Update User Docs

Update every docs/content/ page that describes the changed behaviour, in the same PR. Follow the docs skill.
An API change updates api/*.yaml too.

Read the full file on GitHub · 49 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.

6d ago First seen · 49 lines · 62 tokens per session scan A 1851296c80bb

Subscribe to this mod's changes

spec-sync is a skill published in the GitHub repository thunder-id/thunderid (594 stars, last pushed yesterday), licensed Apache-2.0. It adds 62 tokens to every session and 570 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-10-21.

Go Security Writing and docs access-management authentication authorization go hacktoberfest

coding-directives

Implement or review caddy-security Go code, Caddy modules, parsers, lifecycle, and HTTP delegation. Use for app/plugin boundaries, authcrunch integration, errors, logging, and code conventions.

greenpau/caddy-security · 45 tokens

jwt

Development guide for the jwt JSON Web Token library for Go (github.com/kataras/jwt). Use this skill when signing or verifying JWTs, choosing a signing algorithm (HMAC, RSA, RSA-PSS, ECDSA, EdDSA), reading or validating standard or custom claims, setting expiry and clock-skew tolerance, rotating keys with a kid-based…

kataras/jwt · 107 tokens

thunderid: Skill for Claude Code