Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add vladm3105/aidoc-flow-framework/plugin install aidoc-flowWrote 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/vladm3105/aidoc-flow-framework/adr-roadmap)<a href="https://agentmods.dev/skills/vladm3105/aidoc-flow-framework/adr-roadmap"><img src="https://agentmods.dev/badge/skills/vladm3105/aidoc-flow-framework/adr-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 5.1 | $0.00037 | $0.00960 |
| Opus 5 | $0.00018 | $0.00480 |
| Sonnet 5 | $0.00007 | $0.00192 |
| Haiku 4.5 | $0.00004 | $0.00096 |
Grade A, and why
adr-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 yesterday.
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 — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.
adr-roadmap
Purpose
Analyze a project's Architecture Decision Records (ADRs, Layer 5) and produce a phased implementation roadmap: dependency mapping, critical path, phase decomposition, timeline estimates, per-phase risk assessment, and a testing and technical-debt strategy. Engine-agnostic — works for any domain (web, mobile, data, ML, infrastructure, embedded).
Upstream: ADR. Downstream: feeds SPEC → TDD → IPLAN delivery sequencing.
When to Use
Use adr-roadmap when:
- A project has roughly five or more ADRs that need coordinated, phased rollout.
- You need visibility into architectural dependencies and the critical path.
- Stakeholders need a timeline, milestones, and an executive summary derived from ADR complexity.
Do not use it for a single ADR with a trivial implementation, for
informational ADRs with no build work, when planning from requirements (use
../doc-brd/SKILL.md / ../doc-prd/SKILL.md / ../doc-ears/SKILL.md), or when
you only need diagrams (use ../charts-flow/SKILL.md).
Behavior
- Inventory ADRs — read every
ADR-*.md, extract ID, title, status, complexity (1–5), effort, and dependencies; warn on missing complexity or broken dependency references; error if no ADRs are found. - Build the dependency graph — classify hard / soft / no dependencies, detect cycles (error), compute the critical path, and find clusters that can run in parallel.
- Estimate effort — map complexity to base effort, sum across ADRs, apply a risk buffer (~20%), and flag high-risk ADRs (complexity 4–5 with many deps).
- Form phases — apply the chosen phase model (
poc-mvp-proddefault,iterative, orwaterfall), respecting dependencies, capping phase length (default 8 weeks), isolating risk, and ending phases on natural milestones. Adapt for greenfield, brownfield/migration (add rollback + dual-run), or refactoring (module-by-module) projects. - Build the timeline — derive phase durations from effort and team size,
add inter-phase buffers, and produce a Gantt chart (via
../charts-flow/SKILL.md) with milestones. - Write the roadmap at
{adr_dir}/ADR-00_IMPLEMENTATION-ROADMAP.md: Document Control, executive summary, per-phase sections (objectives, ADRs, architecture diagram, order, deliverables, success/exit criteria, risk), dependency matrix, technical-debt management, risk assessment, testing strategy, and traceability back to upstream (BRD–BDD) and downstream (SPEC/TDD/IPLAN) artifacts.
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.
- yesterday Changed 9ada762ce45b
- 2d ago Changed 0cf50730d28b
- 6d ago First seen · 83 lines · 37 tokens per session scan A b35fcd503b03
adr-roadmap is a skill published in the GitHub repository vladm3105/aidoc-flow-framework (17 stars, last pushed yesterday), licensed MIT. It adds 37 tokens to every session and 960 once invoked, about $0.0002 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 skills, from other repositories
recipe-create-meet-space
Create a Google Meet meeting space and share the join link.
atmos-config
Atmos root configuration: atmos.yaml discovery, precedence, deep merging, basepath, imports, minimal bootstrap, and routing to narrower Atmos skills.
workthreads
SpecStory Workthreads - a weekly work-thread rollup across a team's repos from SpecStory coding histories (any agent - Claude Code, Codex, Cursor, Gemini, and more). It groups the window's sessions into threads of work per project and labels each new / open / recently closed, so a lead sees what shipped, what is still…
story-readiness
Validate that a story file is implementation-ready. Checks for embedded GDD requirements, ADR references, engine notes, clear acceptance criteria, and no open design questions. Produces READY / NEEDS WORK / BLOCKED verdict with specific gaps. Use when user says 'is this story ready', 'can I start on this story', 'is…
autotask-creator
Rules for automation CRUD from the group-chat commander. The commander does not call mutation tools and does not edit cloud/autotasks files directly. It emits one or more top-level ... containers in its final text; the bus parses and applies them after the turn.
monorepo-management
Master monorepo management with Turborepo, Nx, and pnpm workspaces to build efficient, scalable multi-package repositories with optimized builds and dependency management. Use when setting up monorepos, optimizing builds, or managing shared dependencies.