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 ErikaAX08/erikas-skills --skill spec-kit-analyze-consistencygit clone --depth 1 https://github.com/ErikaAX08/erikas-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/erikaax08/erikas-skills/spec-kit-analyze-consistency)<a href="https://agentmods.dev/skills/erikaax08/erikas-skills/spec-kit-analyze-consistency"><img src="https://agentmods.dev/badge/skills/erikaax08/erikas-skills/spec-kit-analyze-consistency/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/erikaax08/erikas-skills/spec-kit-analyze-consistency"><img src="https://agentmods.dev/badge/skills/erikaax08/erikas-skills/spec-kit-analyze-consistency.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 | $0.00097 | $0.04017 |
| Opus 5 | $0.00048 | $0.02008 |
| Sonnet 5 | $0.00019 | $0.00803 |
| Haiku 4.5 | $0.00010 | $0.00402 |
Grade A, and why
spec-kit-analyze-consistency 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 — 311 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Analyze Consistency — Cross-Artifact Verification Skill
Purpose
Answer one question honestly, with evidence: is it safe to move from tasks.md to
spec-kit-execute-tasks? This skill cross-checks spec.md, plan.md, and tasks.md against each other
— coverage, traceability, Safe Deferral consistency, and story-closure completeness — and reports
findings. It is the fourth link in the spec-kit chain, and the only one that is purely
read-only: it never edits spec.md, plan.md, tasks.md, or state.json. If something is
wrong, the fix happens back in spec-kit-generate-spec, spec-kit-generate-plan, or spec-kit-generate-tasks — this skill
only surfaces what needs fixing and how urgently.
User Input
$ARGUMENTS
Always consider the complete user message and any files or attachments available in the current
conversation, even when $ARGUMENTS appears literally or is empty. The most common input is a
reference to a feature directory; this skill checks whatever subset of spec.md/plan.md/
tasks.md actually exists there.
Core Principle
Every finding is a citation, not an impression. Every finding is classified as BLOCKING or
ADVISORY — never left ambiguous about how urgent it is.
- A finding without a concrete ID (an
R-FR##,O-0#,T0##, file/line) is not a finding, it's a hunch — do not report one. BLOCKINGfindings are the ones that meanspec-kit-execute-taskswould build on a gap that can break something (an unverified safeguard, an unsafe deferral, an incomplete story closure, a task with no traceable scope).ADVISORYfindings are real but not urgent enough to halt on their own (an uncovered nice-to-have requirement, terminology drift, an operation without a task in a feature that intentionally stops short of full coverage this release).- This skill does not decide how to fix anything — that is the job of whichever upstream skill owns the artifact with the gap.
Non-Negotiable Rules
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 · 311 lines · 97 tokens per session scan A babae169b461
spec-kit-analyze-consistency is a skill published in the GitHub repository ErikaAX08/erikas-skills (5 stars, last pushed 12d ago), licensed MIT. It adds 97 tokens to every session and 4,017 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
sdd-apply
Skill "sdd-apply" from Gentleman-Programming/gentle-ai, covering execution role, language domain contract, purpose, what you receive and execution and persistence contract.
gentle-ai-collab-perfect
Trigger: contributing to Gentleman-Programming/gentle-ai as an external collaborator. Strict issue-first workflow, honest PR bodies, contributor-vs-maintainer scope, chained-PR strategy, verification protocol, docstring coverage. Load whenever the active repo is Gentleman-Programming/gentle-ai and any part of the…
issue-creation
Trigger: issue creation, bug reports, feature requests, or issue approval. Create and triage GitHub issues from repository evidence.
sdd-spec
Write SDD delta specs with requirements and scenarios. Trigger: orchestrator launches spec work for a change.
sdd-tasks
Break an SDD change into implementation tasks. Trigger: orchestrator launches task planning for a change.
sdd-verify
Skill "sdd-verify" from Gentleman-Programming/gentle-ai, covering execution role, language domain contract, activation contract, hard rules and decision gates.