Borrowing it
Nothing to install: this file belongs to pangon/ai-sdlc-framework. 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/pangon/ai-sdlc-framework/main/.claude/skills/SDLC-validate/SKILL.mdgit clone --depth 1 https://github.com/pangon/ai-sdlc-frameworkWrote 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/pangon/ai-sdlc-framework/sdlc-validate)<a href="https://agentmods.dev/skills/pangon/ai-sdlc-framework/sdlc-validate"><img src="https://agentmods.dev/badge/skills/pangon/ai-sdlc-framework/sdlc-validate/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/pangon/ai-sdlc-framework/sdlc-validate"><img src="https://agentmods.dev/badge/skills/pangon/ai-sdlc-framework/sdlc-validate.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 82 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
- medium Excessive Agency · line 90 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00083 | $0.02444 |
| Opus 5.5 | $0.00033 | $0.00978 |
| Sonnet 5.5 | $0.00017 | $0.00489 |
| Haiku 4.5 | $0.00008 | $0.00244 |
Grade A, and why
SDLC-validate 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 2mo 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 — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Instructions
You are running a read-only consistency validation over the repository's SDLC artifacts. You verify mechanically checkable invariants and report violations — you do not modify any file. This skill is the deep counterpart of /SDLC-status: where the dashboard reads index tables and trusts them, validation opens the artifacts and verifies that the indexes, links, statuses, and Current State tell the truth.
Setup
- Read
CLAUDE.md— the Current State Protocol, the### Current Statecontent, the Phase Gates table, and the artifact naming rules — andFRAMEWORK.md(the framework/project boundary manifest). These are the authorities the checks verify against; do not invent stricter rules than documented. - Read
1-spec/CLAUDE.spec.md(index tables, status lifecycles),2-design/CLAUDE.design.md,3-code/CLAUDE.code.md, and4-deploy/CLAUDE.deploy.md. - Read
1-spec/stakeholders.md. - List artifact files, excluding
_template*.mdfiles:1-spec/goals/,1-spec/user-stories/,1-spec/requirements/,1-spec/assumptions/,1-spec/constraints/,2-design/*.md(excludingCLAUDE.design.md),decisions/(also excludingPROCEDURES.md),3-code/*/CLAUDE.md(component directories),3-code/tasks.md,3-code/verification.mdand3-code/*/verification.md(verification indexes),3-code/implementation-log/,4-deploy/runbooks/. - Open artifact files as required by the checks below.
Checks
Run every check whose subject exists; skip checks whose subject does not exist yet (e.g., task checks before an implementation plan) and list the skips in the report — a phase not yet reached is not a finding.
1. Index ↔ file synchronization
- Every artifact file has exactly one row in its index; every index row's File link resolves to an existing file. This includes the design documents: every
2-design/*.md(excluding the template and the phase file) has a row in the Design Documents Index and vice versa, andarchitecture.mdis always listed. - Index metadata (Type, Status, Priority, link columns) matches the fields inside the artifact file.
- Decision indexes: every
DEC-*.mdwith a matching trigger appears in the corresponding phase/component index; no index lists a decision whose Status isDeprecatedorSuperseded.
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.
- 2mo ago First seen · 105 lines · 83 tokens per session scan A 1aba6611614d
SDLC-validate is a skill published in the GitHub repository pangon/ai-sdlc-framework (130 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 83 tokens to every session and 2,444 once invoked, about $0.0003 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 2026-08-30.
SDLC-validate compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| SDLC-validatepangon/ai-sdlc-framework | Skill | 130 | 2mo ago | Apache-2.0 | A | 83 | Claude Code |
| imagegenopenai/codex | Skill | 133k | yesterday | Apache-2.0 | A | 113 | Codex |
| playwright-climicrosoft/playwright | Skill | 99k | yesterday | Apache-2.0 | A | 19 | Claude Code |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | 4d ago | MIT | A | 200 | Claude Code, Codex |
| systematic-debuggingobra/superpowers | Skill | 313k | 3d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | today | MIT | A | 95 | Claude Code |
| next-partial-prefetching-adoptionvercel/next.js | Skill | 143k | today | MIT | A | 103 | Claude Code |