Borrowing it
Nothing to install: this file belongs to maxwellsantoro/dotrepo. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/maxwellsantoro/dotrepo/main/.agents/skills/roadmap-coordination/SKILL.mdgit clone --depth 1 https://github.com/maxwellsantoro/dotrepoWrote 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/maxwellsantoro/dotrepo/roadmap-coordination)<a href="https://agentmods.dev/skills/maxwellsantoro/dotrepo/roadmap-coordination"><img src="https://agentmods.dev/badge/skills/maxwellsantoro/dotrepo/roadmap-coordination/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/maxwellsantoro/dotrepo/roadmap-coordination"><img src="https://agentmods.dev/badge/skills/maxwellsantoro/dotrepo/roadmap-coordination.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 | $0.00044 | $0.00485 |
| Opus 5.5 | $0.00018 | $0.00194 |
| Sonnet 5.5 | $0.00009 | $0.00097 |
| Haiku 4.5 | $0.00004 | $0.00049 |
Grade A, and why
roadmap-coordination 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 3d 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
Roadmap Coordination
Read AGENTS.md for repository constraints, ROADMAP.md for current packet dependencies and acceptance gates, and the execution guide for the packet, ownership, handoff, and integration protocol. These documents own the process; do not maintain a second task list here.
When the user authorizes a team, act as coordinator or accept a bounded worker packet from the coordinator. Without that authorization, use the same packet and dependency checks with one agent.
- Coordinator: dispatch independently ready packets within available capacity. Use roadmap priority to allocate contested resources and order integration; do not serialize independent preparation behind an outcome gate. Before dispatch, settle shared contract changes and assign disjoint writable paths. Start elapsed-time or external gates early only when the current roadmap selects them and the user has authorized the required actions. Historical pilot packets do not schedule recruitment or block local workflow controls. In one shared checkout, only the coordinator switches branches — workers use worktrees or hand back diffs for the coordinator to apply (see the execution guide). Batch waves by CI scope (prose → Python/workflows → Rust) and run the full gate once per integrated wave, not once per worker.
- Worker: follow the assigned scope, produce the acceptance evidence, and hand back a focused diff plus checks and remaining dependencies using the execution guide. Ask the coordinator to resolve ownership overlap before editing it.
- Coordinator: integrate at a named checkpoint, verify affected shared contracts, and run combined gates once the relevant changes settle. Record unfinished outcomes as pending even when their implementation has passed its tests.
The roadmap separates agent-completable work from operations, publication, consenting external use, and growth evidence. Keep those joins explicit; a reference harness, a prepared release, or operator traffic cannot close them. Use the agent models configured by the environment. The crawler's adjudication provider policy is a separate project configuration, not a worker assignment.
What ships with it
1 file 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.
- 3d ago Changed · +1 lines 07a1c7eef1f2
- 9d ago Changed · +6 lines 9e6b85339ed4
- 1mo ago First seen · 34 lines · 44 tokens per session scan A 4f8d206e40d3
roadmap-coordination is a skill published in the GitHub repository maxwellsantoro/dotrepo (1 stars, last pushed 4d ago), licensed MIT. It adds 44 tokens to every session and 485 once invoked, about $0.0002 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 2026-10-06.
roadmap-coordination compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| roadmap-coordinationmaxwellsantoro/dotrepo | Skill | 1 | 4d ago | MIT | A | 44 | Codex |
| lsp-inspectblackwell-systems/agent-lsp | Skill | 172 | yesterday | MIT | A | 126 | Claude Code |
| lsp-refactorblackwell-systems/agent-lsp | Skill | 172 | yesterday | MIT | A | 57 | Claude Code |
| lsp-dead-codeblackwell-systems/agent-lsp | Skill | 172 | yesterday | MIT | A | 43 | Claude Code |
| lsp-edit-exportblackwell-systems/agent-lsp | Skill | 172 | yesterday | MIT | A | 46 | Claude Code |
| lsp-impactblackwell-systems/agent-lsp | Skill | 172 | yesterday | MIT | A | 67 | Claude Code |
| lsp-exploreblackwell-systems/agent-lsp | Skill | 172 | yesterday | MIT | A | 29 | Claude Code |