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 eduardohki/code-agent-plugins --skill shape-featuresgit clone --depth 1 https://github.com/eduardohki/code-agent-pluginsWrote 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/eduardohki/code-agent-plugins/shape-features)<a href="https://agentmods.dev/skills/eduardohki/code-agent-plugins/shape-features"><img src="https://agentmods.dev/badge/skills/eduardohki/code-agent-plugins/shape-features/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/eduardohki/code-agent-plugins/shape-features"><img src="https://agentmods.dev/badge/skills/eduardohki/code-agent-plugins/shape-features.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 | $0.00080 | $0.01819 |
| Opus 5.5 | $0.00032 | $0.00728 |
| Sonnet 5.5 | $0.00016 | $0.00364 |
| Haiku 4.5 | $0.00008 | $0.00182 |
Grade A, and why
shape-features 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 — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Shape Features
Overview
Guided workflow for producing, auditing, or learning about software requirements. Routes to one of three sub-workflows based on the user's goal.
Quick Reference
| Goal | Workflow |
|---|---|
| Shape a new feature from any input | shape-new-feature-workflow.md |
| Audit or review existing requirements | review-existing-workflow.md |
| Learn what good requirements look like | learn-the-practice-workflow.md |
Each workflow opens with its own Required Reading section; the full reference list with loading guidance is in the Reference Index below.
Intake & Routing
Route directly when intent is clear from the user's message - do not present the menu first:
- User pastes requirements or a feature spec, or links to one → review-existing-workflow.md
- User describes a feature they want to build → shape-new-feature-workflow.md
- User asks "what makes good requirements" or similar → learn-the-practice-workflow.md
- User provides meeting notes or a product brief → shape-new-feature workflow (treat as input material)
- User has a feature in production and wants to refine the next iteration → review workflow (audit first, then re-plan)
The user may arrive with meeting notes, product briefs, external documentation, or a rough feature idea. All starting points are valid - the skill steers toward quality regardless of where the input came from.
Only when intent is genuinely ambiguous, present the menu and wait for a response before proceeding:
What would you like to do?
- Shape a new feature - collect and structure its requirements
- Review/audit existing requirements
- Learn what good requirements look like (and common pitfalls)
Not sure which applies? Starting fresh on a new feature → 1. Already have stories / a PRD / backlog items you want checked → 2. No specific feature yet, want to understand the practice first → 3.
What ships with it
15 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.
- assets/feature-requirements.md 6.0 KB
- README.md 12 KB
- references/adapting-to-your-context.md 11 KB
- references/bdd-and-acceptance-criteria.md 12 KB
- references/common-pitfalls.md 24 KB
- references/essential-principles.md 9.1 KB
- references/glossary.md 5.6 KB
- references/known-limitations.md 8.7 KB
- references/learn-the-practice-workflow.md 11 KB
- references/review-examples.md 21 KB
- references/review-existing-workflow.md 19 KB
- references/shape-new-feature-workflow.md 21 KB
- references/story-slicing-and-sizing.md 23 KB
- references/what-good-looks-like.md 8.4 KB
- references/worked-example.md 20 KB
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 · 106 lines · 80 tokens per session scan A fbbc7cd95c9d
shape-features is a skill published in the GitHub repository eduardohki/code-agent-plugins (2 stars, last pushed 2mo ago), licensed MIT. It adds 80 tokens to every session and 1,819 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 2026-08-31.
shape-features compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| shape-featureseduardohki/code-agent-plugins | Skill | 2 | 2mo ago | MIT | A | 80 | Claude Code |
| imagegenopenai/codex | Skill | 134k | today | Apache-2.0 | A | 113 | Codex |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | today | MIT | A | 200 | Claude Code, Codex |
| playwright-climicrosoft/playwright | Skill | 99k | today | Apache-2.0 | A | 19 | Claude Code |
| systematic-debuggingobra/superpowers | Skill | 314k | 4d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | today | MIT | A | 95 | Claude Code |
| chat-pet-sprite-creationmicrosoft/vscode | Skill | 195k | today | MIT | A | 53 | Claude Code, Codex |