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 Aimeerrhythm/enterprise-change-workflow --skill spec-challengegit clone --depth 1 https://github.com/Aimeerrhythm/enterprise-change-workflowWrote 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/aimeerrhythm/enterprise-change-workflow/spec-challenge)<a href="https://agentmods.dev/skills/aimeerrhythm/enterprise-change-workflow/spec-challenge"><img src="https://agentmods.dev/badge/skills/aimeerrhythm/enterprise-change-workflow/spec-challenge/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/aimeerrhythm/enterprise-change-workflow/spec-challenge"><img src="https://agentmods.dev/badge/skills/aimeerrhythm/enterprise-change-workflow/spec-challenge.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 | $0.00045 | $0.02177 |
| Opus 5 | $0.00023 | $0.01089 |
| Sonnet 5 | $0.00009 | $0.00435 |
| Haiku 4.5 | $0.00005 | $0.00218 |
Grade A, and why
spec-challenge 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 8d 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 — 187 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Spec Challenge — Adversarial Plan Review
After a plan/design document is produced, dispatch the spec-challenge agent for independent adversarial review. Present the review report to the user, who confirms handling for each item.
Announce at start: "Using ecw:spec-challenge for adversarial plan review."
Output language: Read ecw.yml → project.output_language. Pass to dispatched agent prompt. Report headings and labels follow this language.
Flow
digraph spec_challenge {
rankdir=TB;
"Collect review materials" [shape=box];
"Dispatch spec-challenge agent" [shape=box];
"Present review report" [shape=box];
"Per-item user confirmation" [shape=box];
"Author executes per user decisions" [shape=box];
"Output response summary" [shape=box];
"User final confirmation" [shape=box];
"Review passed" [shape=doublecircle];
"Collect review materials" -> "Dispatch spec-challenge agent";
"Dispatch spec-challenge agent" -> "Present review report";
"Present review report" -> "Per-item user confirmation";
"Per-item user confirmation" -> "Author executes per user decisions";
"Author executes per user decisions" -> "Output response summary";
"Output response summary" -> "User final confirmation";
"User final confirmation" -> "Review passed";
}
Key Rule: User Drives Decisions
After spec-challenge report returns, AI must NOT respond on its own. Follow these steps strictly:
- Present — Display the full spec-challenge review report verbatim
- Per-item confirmation — For each fatal flaw (F1, F2, ...), use AskUserQuestion to let user choose handling:
- ✅ Agree to modify — AI executes the modification
- ❌ Disagree — User provides rationale, or AI drafts technical rebuttal for user confirmation
- ❓ Needs discussion — Enter discussion until user decides
- Batch confirm improvements — Improvement suggestions (I1, I2, ...) can be presented at once, letting user multi-select which to adopt/defer
- Execute — AI executes per user-confirmed decisions
- Final confirmation — Output response summary, review passes after user confirms
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 8d ago First seen · 187 lines · 45 tokens per session scan A 149c88d813d8
spec-challenge is a skill published in the GitHub repository Aimeerrhythm/enterprise-change-workflow (1 stars, last pushed 3mo ago), licensed MIT. It adds 45 tokens to every session and 2,177 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 2026-08-31.
Other skills, from other repositories
g-review
Run the review gate on the current branch diff. Runs the test suite, captures the diff, and dispatches code-lead, which verifies done conditions and reviews the diff itself. Issues MERGE READY or HOLD.
g-audit
Full-codebase or targeted code quality audit. Detects SOLID violations, code smells, architectural drift, dead code, and test coverage gaps. Targeted scope produces an inline report. Whole-codebase scope produces a prioritised roadmap milestone.
g-refactor
Guided refactor workflow — identify target, pre-analyse, spec, approve, execute, review. Accepts a scope path, an audit milestone file, or runs interactively. Safe-by-default: checks test coverage before execution and runs the full review gate after.
g-blast-radius
Analyse the blast radius of a planned change. Inputs a file path, feature name, or list of paths from a plan. Outputs the set of dependent files (forward and reverse references), a per-file volatility score (commit frequency proxy), and a total blast-radius rating (low / moderate / wide). Read-only.
cross-verify
A cross-checking skill that reviews decisions, designs, documents, and implementations from four viewpoints.
decompose
Break a large goal into 3–8 sequenced tasks, each one /eng → /tdd cycle. Writes to specs/{slug}.todos.md when a spec exists, root TODOS.md otherwise. /decompose — decompose a feature or goal /decompose re-entry — resume where you left off (auto-detected).