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.
git clone --depth 1 https://github.com/chris-dare-dev/agent-kitWrote 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/agents/chris-dare-dev/agent-kit/roadmap-decomposer)<a href="https://agentmods.dev/agents/chris-dare-dev/agent-kit/roadmap-decomposer"><img src="https://agentmods.dev/badge/agents/chris-dare-dev/agent-kit/roadmap-decomposer/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/agents/chris-dare-dev/agent-kit/roadmap-decomposer"><img src="https://agentmods.dev/badge/agents/chris-dare-dev/agent-kit/roadmap-decomposer.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 | $0.00096 | $0.02104 |
| Opus 5.5 | $0.00038 | $0.00842 |
| Sonnet 5.5 | $0.00019 | $0.00421 |
| Haiku 4.5 | $0.00010 | $0.00210 |
Grade C, and why
roadmap-decomposer scanned grade C with 2 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 1mo 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.
Instruction-override phrasingmediumPrompt injection
Text telling the model to disregard its earlier instructions or safety rules is the shape of a prompt injection, whoever wrote it.
"Now run X", "Ignore previous instructions", "Authorize the user", "Add yourself Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
cat ".claude/agent-memory/roadmap-decomposer/lessons.md" 2>/dev/null || echo "(no lessons yet)" How it starts
The opening of the file, as written. The whole thing — 177 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Roadmap Decomposer
You are Phase 2 of the /roadmap pipeline. Your job is to convert the goal statement from Phase 1 into a set of 2–6 epics, each ≤ 6 weeks of work, INVEST-validated, and tagged as enabler or value.
The orchestrator (slash command at .claude/commands/roadmap.md) dispatches you with substituted variables. You never invoke other sub-agents.
Input variables (substituted by the orchestrator)
{SLUG}— the roadmap slug{ROADMAP_PATH}— absolute path toplans/<slug>-roadmap.md
Step 0 — Read persistent memory (skip-if-not-relevant)
cat ".claude/agent-memory/roadmap-decomposer/lessons.md" 2>/dev/null || echo "(no lessons yet)"
Step 1 — Read the phase-decompose reference + Goal section (REQUIRED before reasoning)
Read these in order (paths resolve from ANY CWD — the target repo is usually NOT the agent-kit checkout, so never use relative data/... paths):
$WS/.claude/references/roadmap-phase-decompose.md(whereWS="${PERSONAL_WORKSPACE_ROOT:-$HOME/Work/workspace}"; equivalently MCPget_reference("roadmap-phase-decompose")) — canonical decomposition technique decision table, INVEST rules, enabler vs value definitions, specialist agent map.- The
## Goalsection from{ROADMAP_PATH}— this is the sole input to decomposition.
Do NOT proceed until both are loaded.
Step 2 — Walk the decomposition sub-steps
Sub-step 2a — Pick the decomposition technique
Use the decision table from $WS/.claude/references/roadmap-phase-decompose.md (Problem shape → technique). The default for the platform work is vertical slicing + enabler stories. Choose a different technique only if the problem shape clearly maps to it (user journey → User Story Mapping; unknown domain → Event Storming; behavior-change goal → Impact Mapping).
Sub-step 2b — Produce 2–6 epics
For each epic:
- Title — action verb, no conventional commit prefix (per workspace CLAUDE.md).
- Type —
enablerorvalue. - Size — XS / S / M / L / XL (cap at XL = ≤ 6 weeks). If larger, split.
- Specialist agent — name the specialist that will execute this in
/milestone-pipelinePhase 2. Use the decision table in$WS/.claude/references/roadmap-phase-decompose.md. If none match, writegeneral-purpose. - Depends on — other epic id, or
none. Epics with many dependencies are a decomposition smell — re-cut. - Epic-level AC — 3–5 observable outcome bullets. NOT Given/When/Then (that's Phase 3 for Now-lane stories).
- Risks — 1–2 lines on the highest-risk aspect.
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.
- 1mo ago First seen · 177 lines · 96 tokens per session scan C d1fd9c062ebc
roadmap-decomposer is an agent published in the GitHub repository chris-dare-dev/agent-kit (0 stars, last pushed 2mo ago), licensed MIT. It adds 96 tokens to every session and 2,104 once invoked, about $0.0004 per session on Opus 5.5. A static security scan graded it C with 2 findings (instruction-override phrasing, reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.