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 wedabro/bro-skills --skill speckit.roadmapgit clone --depth 1 https://github.com/wedabro/bro-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/skills/wedabro/bro-skills/speckit.roadmap)<a href="https://agentmods.dev/skills/wedabro/bro-skills/speckit.roadmap"><img src="https://agentmods.dev/badge/skills/wedabro/bro-skills/speckit.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/wedabro/bro-skills/speckit.roadmap"><img src="https://agentmods.dev/badge/skills/wedabro/bro-skills/speckit.roadmap.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 | $0.00025 | $0.00329 |
| Opus 5.5 | $0.00010 | $0.00132 |
| Sonnet 5.5 | $0.00005 | $0.00066 |
| Haiku 4.5 | $0.00003 | $0.00033 |
Grade A, and why
speckit.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.
What it actually says
Mission
Keep .agents/ROADMAP.md aligned with approved scope, implementation evidence, and release gates.
Inputs and Outputs
- Read constitution, feature specs/plans/tasks, status reports, backlog/debt, and existing ROADMAP.md.
- Write or update ROADMAP.md with milestones, phases, dependencies, owners, target signals, risks, and transition decisions.
Protocol
1. Baseline and Scope
- Identify goal, current phase, milestones, user stories, mandatory security/DevOps gates, and out-of-scope work. Preserve completed history and stable IDs.
2. Milestone Design
- Define outcome, measurable exit criteria, included phases, dependencies, owner, and evidence links. Order phases by dependency.
3. Progress Reconciliation
- Compare roadmap with status reports, tasks, tests, reviews, and backlog. Complete a phase only when exit criteria have evidence; record blockers and next owner.
4. Transition Decision
- Choose continue, hold, re-plan, or close at boundaries and explain unresolved conditions. Never skip mandatory gates or delete unfinished milestones.
Completion Gate
Every active phase maps to tasks, milestones have measurable exit criteria, status claims cite evidence, and mandatory security/DevOps gates are represented.
Guard Rails
- Do not rewrite history, invent dates/owners, or mark delivery complete without evidence.
- Do not skip mandatory security or DevOps phases or delete roadmap items without authorization.
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 Changed · +2 lines · -2 tokens per session cb459b2507e4
- 2mo ago First seen · 26 lines · 27 tokens per session scan A 0771801dbbcd
speckit.roadmap is a skill published in the GitHub repository wedabro/bro-skills (3 stars, last pushed 17d ago), licensed MIT. It adds 25 tokens to every session and 329 once invoked, about $0.0001 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.
Other skills, from other repositories
working-days-get-working-days
Calculate the number of working days between two dates, optionally accounting for country-specific holidays.
pm-karpathy-thinking
Stress-test a product decision, PRD, roadmap, experiment, or feature proposal using explicit assumptions, simplicity-first scope, surgical changes, and measurable verification loops. Use when product work is ambiguous, over-scoped, solution-led, risky, or needs a clear go/no-go recommendation.
pm-vietnamese
Create decision-ready, delivery-ready bilingual Vietnamese-English product management artifacts. Use for discovery, PRDs, user stories, prioritization, roadmaps, OKRs, metrics, experiment plans, feedback analysis, meeting synthesis, stakeholder updates, and pre-mortems.
pm-bilingual
Create concise bilingual Vietnamese-English product management artifacts and translate PM context accurately across both languages. Use for bilingual PRDs, discovery briefs, user stories, prioritization memos, metric plans, meeting decisions, stakeholder updates, and Vietnamese-English PM terminology.
wayfinder
Plan a huge chunk of work (more than one agent session can hold) as a shared map of decision tickets on your issue tracker, and resolve them one at a time until the way to the destination is clear.
stakeholder-update
Drafts a weekly update, executive summary, escalation, or launch announcement for readers outside the working group. Use when preparing status or launch communication for leadership, partners, or customers.