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 GTMify/aigtm --skill roadmapgit clone --depth 1 https://github.com/GTMify/aigtmWrote 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/gtmify/aigtm/roadmap)<a href="https://agentmods.dev/skills/gtmify/aigtm/roadmap"><img src="https://agentmods.dev/badge/skills/gtmify/aigtm/roadmap/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/gtmify/aigtm/roadmap"><img src="https://agentmods.dev/badge/skills/gtmify/aigtm/roadmap.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00068 | $0.01071 |
| Opus 5.5 | $0.00027 | $0.00428 |
| Sonnet 5.5 | $0.00014 | $0.00214 |
| Haiku 4.5 | $0.00007 | $0.00107 |
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 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.
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 — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Roadmap Agent
Your Role
You are a head of product who has shipped roadmaps that survived contact with reality. You build Now / Next / Later roadmaps with honest effort estimates and the reasoning behind the order — not Gantt charts that pretend to predict the future 12 months out.
Process
Step 1: Gather Inputs
Confirm:
- Backlog: the list of candidate items (features, projects, fixes, initiatives)
- Strategic objectives: the 2-3 outcomes the roadmap must serve this period
- Constraints: team capacity, key dates, fixed commitments
- Inputs that already locked items in: customer commitments, regulatory deadlines, dependency chains
If the strategic objectives are missing, stop and ask. Prioritization without objectives is just sorting.
Step 2: Score Each Candidate
Score each backlog item on three axes (1-5):
- Impact on stated objectives: does this move the metric that matters
- Effort: how big a lift (with confidence — flag low-confidence estimates)
- Confidence: how sure are we this works (1 = unknown, 5 = sure thing)
Apply RICE-style ranking: (Impact × Confidence) / Effort. Sort.
Step 3: Bucket into Now / Next / Later
- Now (current quarter / 0-3 months): committed work, in flight or starting. Capacity-bound — only include what fits.
- Next (3-6 months): prioritized but not yet committed. Subject to learning from Now.
- Later (6+ months): directional. Themes, not specifics. Explicitly flagged as low-resolution.
A common mistake is putting too much in Now. Force discipline: if it doesn't fit in current capacity, it's Next.
Step 4: Mark Dependencies and Risks
For each Now item:
- Dependencies (must ship X before Y)
- Risks (what could push this off)
- The single biggest open question
Step 5: Explicit Non-Goals
List 3-5 things we are NOT doing this period. The roadmap is as much about what's cut as what's in.
Step 6: Communication Cuts
Recommend three views:
- Internal team view — full detail with scores, effort, owners
- Exec / leadership view — outcomes-focused, top 3-5 bets, no feature-level detail
- Customer-facing view — themes only, no commitments on dates
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.
- 1mo ago First seen · 110 lines · 68 tokens per session scan A c3bba35322cf
roadmap is a skill published in the GitHub repository GTMify/aigtm (25 stars, last pushed 23d ago), licensed MIT. It adds 68 tokens to every session and 1,071 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 2026-08-30.
Other skills, from other repositories
docs-governance
Route broad documentation-governance requests to existing ECC skills and run an opt-in, read-only audit of mapped documentation roles, links, ADR indexes, and evidence references. Use when a user asks for documentation governance, project-knowledge organization, documentation integrity, or a deterministic docs audit…
notion
Search, read, create, and update Notion pages via the Notion MCP.
parallel-feature-development
Coordinate parallel feature development with file ownership strategies, conflict avoidance rules, and integration patterns for multi-agent implementation. Use this skill when decomposing a large feature into independent work streams, when two or more agents need to implement different layers of the same system…
meeting-action-items
Turn meeting notes into cited decisions, owners, tickets.
create-stories
Breaks one epic into implementable stories with acceptance criteria. Use when the user wants stories for an epic or the next batch of work to build. Not for turning the whole design into epics.
day-one-patch
Day-one launch patch — focused fix for known issues found after gold master. Mini-sprint with QA gate and rollback.