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.
curl -O https://raw.githubusercontent.com/doncheli/don-cheli-sdd/main/.agent/skills/doncheli-drift/SKILL.mdgit clone --depth 1 https://github.com/doncheli/don-cheli-sddWrote 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/doncheli/don-cheli-sdd/doncheli-drift)<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.
<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>- NVIDIA SkillSpector pass
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 | $0.00044 | $0.00461 |
| Opus 5 | $0.00022 | $0.00230 |
| Sonnet 5 | $0.00009 | $0.00092 |
| Haiku 4.5 | $0.00004 | $0.00046 |
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.
What it actually says
Don Cheli: Spec Drift Detector
Instructions
- Read the current spec files in
.dc/specs/and the relevant source code - Compare spec scenarios (Gherkin / acceptance criteria) against the actual implementation
- 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
- For each drift finding, report: file path, spec reference, severity (critical / warning / info)
- Propose a reconciliation: either update the spec or flag the code for correction
- Never auto-modify code — output a reconciliation plan for human approval
- Save a drift report to
.dc/drift-report-<date>.mdif findings exceed 3 items - 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)
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.
- 10d ago First seen · 46 lines · 44 tokens per session scan A 3cb881032c09
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.
Other skills, from other repositories
ship
Create a rich PR from planning artifacts (SUMMARY one-liners, requirement coverage, verification status).
review-pr
Perform a comprehensive code review of a pull request.
sonarqube
Analyze SonarCloud quality issues for a specific PR.
eval-rules
Audit .claude/rules/ files for structural correctness, glob validity, and real-world usefulness. Resolves each paths: pattern against actual project files, then asks the user whether each rule is still relevant and useful. Can update rules in-place based on answers. Use when setting up rules for the first time…
refactor
Analyze code for SOLID violations and suggest targeted improvements.
arrow-maintenance
Navigation and audit overlay for linked-intent development. Use when working with docs/arrows/ — orienting via index.yaml, auditing spec-to-code coherence, detecting reverse orphans and drift, splitting/merging/renaming/re-parenting segments. Dual-mode: ambient guidance when the overlay is present…