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 commands/elct9620/ai-coding-skills/roadmapgit clone --depth 1 https://github.com/elct9620/ai-coding-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/commands/elct9620/ai-coding-skills/roadmap)<a href="https://agentmods.dev/commands/elct9620/ai-coding-skills/roadmap"><img src="https://agentmods.dev/badge/commands/elct9620/ai-coding-skills/roadmap.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 | $0.00053 | $0.03457 |
| Opus 5 | $0.00026 | $0.01729 |
| Sonnet 5 | $0.00011 | $0.00691 |
| Haiku 4.5 | $0.00005 | $0.00346 |
Grade A, and why
roadmap 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 4d 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 — 211 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Rule
The <execute name="main">ARGUMENTS</execute> is entry point for this command.
ROADMAP.md Format
ROADMAP.md acts as a spec-to-implementation index. It tracks the project's feature list — the features the spec commits to — and records the implementation status of each, one row per feature, so the whole thing stays scannable at a glance.
A spec is organized by layers (intent, behaviors, terminology), not by feature, and its shape changes with size: a small project keeps everything inline in SPEC.md, a larger one splits each feature into its own detail document. A roadmap row maps to a feature wherever it lives — an inline section, a group of behaviors, or a linked detail document — and follows the spec's own feature order. Supporting content such as purpose, terminology, or cross-cutting error scenarios is not a feature and gets no row.
The roadmap's sectioning mirrors the spec's context boundaries, never its feature granularity. When the spec keeps everything in one context, the roadmap is a single flat table with no headings. When the spec partitions features by bounded context or domain — grouping them under context headings in Scope, or splitting detail documents into context groups — give each context its own ## [Context] heading with its own flat feature table, in the spec's order. Either way, a feature is never its own section.
The description paragraph below the heading summarizes the project's purpose and key features, giving readers immediate context without needing to read the full spec.
Single context — one flat table:
# Roadmap
A task management app built with Rails. Features include user authentication,
billing with Stripe integration, and team-based task management.
| Feature | Entry Points | Notes |
|---------|-------------|-------|
| ✅ [User Authentication](SPEC.md#user-authentication) | [src/auth/](src/auth/) | JWT-based, refresh token rotation |
| 📌 [Task Management](SPEC.md#task-management) | — | Not started |
| ⏳ [Billing](docs/billing.md) | [src/billing/](src/billing/) | Plan validation only; payment and cancel missing |
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.
- 4d ago First seen · 211 lines · 0 tokens per session scan A 86bff1926189
roadmap is a command published in the GitHub repository elct9620/ai-coding-skills (5 stars, last pushed 9d ago), licensed Apache-2.0. It adds 53 tokens to every session and 3,457 once invoked, about $0.0003 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 commands, from other repositories
git
Git operations with intelligent commit messages and workflow optimization.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.