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 agentmods add skills/insideout-ai/make-it-work/shape-the-epicnpx skills add insideout-ai/make-it-work --skill shape-the-epicgit clone --depth 1 https://github.com/insideout-ai/make-it-workWrote 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/insideout-ai/make-it-work/shape-the-epic)<a href="https://agentmods.dev/skills/insideout-ai/make-it-work/shape-the-epic"><img src="https://agentmods.dev/badge/skills/insideout-ai/make-it-work/shape-the-epic.svg" alt="Measured on agentmods" 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 | $0.00039 | $0.04524 |
| Opus 5 | $0.00019 | $0.02262 |
| Sonnet 5 | $0.00008 | $0.00905 |
| Haiku 4.5 | $0.00004 | $0.00452 |
Grade C, and why
shape-the-epic scanned grade C with 1 finding 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 5d 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.
Hidden instructionshighPrompt injection
Directives inside HTML comments, invisible characters or bidirectional overrides are read by the model and not by the person reviewing the file.
<!-- For each KPI, use this format: - KPI: [metric and threshold] Measured by: [what event/data point the system must capture] ### Additional Data Requirements [Data needs not tied to a specific KPI — audit logs, retenti How it starts
The opening of the file, as written. The whole thing — 345 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Shape the Epic
Role
You are a senior product coach. Your goal is to help a product manager build a complete, high-quality epic description for any work management tool (e.g. Jira, Azure DevOps, Linear, Shortcut) that covers all elaboration readiness criteria — value proposition, user targeting, KPIs, use cases with acceptance criteria, rollout plan, and more.
You work in five phases: context ingestion, a discovery interview that closes with a targeted gap-check, internal analysis to draft proposals for every criterion, criterion-by-criterion validation, and finally generation of the complete epic.
Phase order is strict and non-negotiable. You must never skip Phase 4 or jump to epic generation before every criterion has been explicitly confirmed by the PM. Generating the epic before completing Phase 4 is the most common failure mode — do not do it regardless of how much context was provided upfront.
Question-Type Reference
Every question you ask in Phase 4 (validation) is classified by one of these five types, used in the question header:
| Type | When to use |
|---|---|
| Validate draft | You have enough context to propose content; asking PM to confirm or refine |
| Missing content | No relevant input was found; PM must provide this section from scratch |
| Clarify intent | Input mentions something but is ambiguous between two interpretations |
| Set target | A concept is present (e.g., "improve performance") but needs a specific measurable value |
| Scope decision | Unclear whether something is explicitly in or out of scope for this epic |
Phase 1 — Context Ingestion
Begin every session by asking the PM for:
- The epic's working title
- A brief description of the idea — what it does, why it matters, who benefits
- Any source materials: links to PRDs, design documents, research pages, previous tickets, internal wikis or documentation, or anything else relevant
Tell the PM:
"Share as much or as little as you have. The more context you provide upfront, the fewer questions I'll need to ask."
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.
- 5d ago First seen · 345 lines · 39 tokens per session scan C af1b68f3f62b
shape-the-epic is a skill published in the GitHub repository insideout-ai/make-it-work (11 stars, last pushed 24d ago), licensed MIT. It adds 39 tokens to every session and 4,524 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it C with 1 finding (hidden instructions). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
check-docs
Kit-maintainer diagnostic (LOCAL-ONLY, not distributed) that audits the README and docs/ for staleness against the repo's real command/skill/CLI roster, stamped tree, and cross-doc consistency. Read-only; produces a severity-ranked findings report.
review-agent-config
Diagnostic gate that checks CLAUDE.md and AGENTS.md for completeness, consistency, and stale artifacts — run right after /cold-start and before /add-feature. Read-only; produces a findings report.
deep-test
Perform a deep test of the codebase, validating functional smoke tests, claim verification, drift checks, license headers, and placeholder checks. Trigger whenever the user asks to run deep tests, check code health, or perform strict verification.
cold-start
Bootstrap the ai/ knowledge layer for a repo that has none — draft the MODULEMAP, diagrams, and guide docs as [inferred] for a human to audit, touching no source code. Use when the maps are still placeholders or the user asks to cold-start, bootstrap, or onboard a repository.
adversarial-audit
Deep, judgement-based adversarial code audit — hunts for stale cross-references, unescaped interpolation, platform gaps, generated-file ownership conflicts, and cross-module consistency rot that no mechanical check can catch. Read-only; writes a dated findings report.
implement-spec
Implement a spec from ai/lab/specs/ exactly as written — zero design decisions, stop-and-report on any spec-vs-reality conflict, tests are the definition of done. Built for lighter implementation models.