don-cheli-sdd: Skill for Claude Code

.agent/skills/doncheli-drift/SKILL.md

doncheli-drift is a skill for Claude Code from doncheli/don-cheli-sdd. It costs 44 tokens per session (461 once invoked), scanned A, original, Apache-2.0.

A specification comparison tool that checks whether documented requirements match the code. It labels differences as code without a specification, a specification without code, or behavior that differs from the specification.

In plain words
What is it for?
Use it to compare Gherkin scenarios or acceptance criteria in the specification folder with the relevant source code. It reports file locations, severity, and whether the specification or code should be corrected.
Why use it?
It helps find features that were added without documentation, requirements that were never implemented, and behavior that changed during development. The result is a reconciliation plan for a person to approve.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

This is doncheli/don-cheli-sdd's own configuration. It tells Claude Code how to work on don-cheli-sdd itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything don-cheli-sdd configures →

Part of the don-cheli-sdd plugin — 28 skills, 115 commands, 1 agent shipped together

Reuse

Borrowing it

Nothing to install: this file belongs to doncheli/don-cheli-sdd. 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/doncheli/don-cheli-sdd/main/.agent/skills/doncheli-drift/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/doncheli/don-cheli-sdd

Made for: Claude Code.

Or install don-cheli-sdd, the plugin that ships this one along with the rest of its 28 skills, 115 commands, 1 agent.

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 doncheli-drift

README.md
[![agentmods](https://agentmods.dev/badge/skills/doncheli/don-cheli-sdd/doncheli-drift/github.svg)](https://agentmods.dev/skills/doncheli/don-cheli-sdd/doncheli-drift)
Your own site
<a href="https://agentmods.dev/skills/doncheli/don-cheli-sdd/doncheli-drift"><img src="https://agentmods.dev/badge/skills/doncheli/don-cheli-sdd/doncheli-drift/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 doncheli-drift

Your own site · 80×15
<a href="https://agentmods.dev/skills/doncheli/don-cheli-sdd/doncheli-drift"><img src="https://agentmods.dev/badge/skills/doncheli/don-cheli-sdd/doncheli-drift.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 44 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 461 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00044 $0.00461
Opus 5 $0.00022 $0.00230
Sonnet 5 $0.00009 $0.00092
Haiku 4.5 $0.00004 $0.00046

Measured 10d ago against content hash 3cb881032c09, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

doncheli-drift 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 10d 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/doncheli-drift/SKILL.md · 46 lines

What it actually says

Don Cheli: Spec Drift Detector

Instructions

  1. Read the current spec files in .dc/specs/ and the relevant source code
  2. Compare spec scenarios (Gherkin / acceptance criteria) against the actual implementation
  3. Identify three categories of drift:
    • Ghost: code exists but no spec covers it
    • Phantom: spec exists but no code implements it
    • Mutant: code and spec exist but behavior diverges
  4. For each drift finding, report: file path, spec reference, severity (critical / warning / info)
  5. Propose a reconciliation: either update the spec or flag the code for correction
  6. Never auto-modify code — output a reconciliation plan for human approval
  7. Save a drift report to .dc/drift-report-<date>.md if findings exceed 3 items
  8. If zero drift is found, confirm with a brief "No drift detected — spec and code are aligned"

Output Format

## Drift Report — <date>

### Ghost (code without spec)
- src/payments/refund.ts:42 — no spec covers the refund edge case

### Phantom (spec without code)
- specs/checkout.feature:Scenario 3 — "Apply coupon on mobile" — not implemented

### Mutant (behavior mismatch)
- specs/auth.feature:Scenario 1 expects 401 on expired token; code returns 403

### Reconciliation Plan
1. [Phantom] Implement "Apply coupon on mobile" or mark as backlog in .dc/backlog.md
2. [Mutant] Fix auth.ts to return 401 — spec is correct per RFC 7235
3. [Ghost] Add spec for refund edge case before next release

Do not use this skill when

  • The user only wants to run tests (use doncheli-tea instead)
  • The spec has not been written yet (use dc:especificar first)
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. 10d ago First seen · 46 lines · 44 tokens per session scan A 3cb881032c09

Subscribe to this mod's changes

doncheli-drift is a skill published in the GitHub repository doncheli/don-cheli-sdd (57 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 44 tokens to every session and 461 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 2026-08-30.