Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/wlfghdr/agentic-kbnpx agentmods add skills/wlfghdr/agentic-kb/kb-roadmapWrote 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/wlfghdr/agentic-kb/kb-roadmap)<a href="https://agentmods.dev/skills/wlfghdr/agentic-kb/kb-roadmap"><img src="https://agentmods.dev/badge/skills/wlfghdr/agentic-kb/kb-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/wlfghdr/agentic-kb/kb-roadmap"><img src="https://agentmods.dev/badge/skills/wlfghdr/agentic-kb/kb-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 | $0.00084 | $0.04152 |
| Opus 5.5 | $0.00034 | $0.01661 |
| Sonnet 5.5 | $0.00017 | $0.00830 |
| Haiku 4.5 | $0.00008 | $0.00415 |
Grade A, and why
kb-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 6d 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 — 253 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill: KB Roadmap
Organizations always have at least two sources of planning truth — tickets and the repository, milestones and delivery, OKRs and commits. They drift. Manual reconciliation is expensive and always stale. This skill closes the loop: it ingests plan + delivery, correlates them across a five-tier ladder, and produces a roadmap artifact that says what is planned, what is delivered, and where the two disagree.
This skill is vendor-neutral. All vocabulary specific to a particular tracker, repository host, or organization lives in the adopter's .kb-config/layers.yaml and .kb-config/artifacts.yaml, never in this skill.
The roadmap is a product-management artifact, not just a tracker report. Its job is to make planned customer/user value, confidence, delivery reality, and source traceability visible in one place.
The skill resolves its roadmap: block from the active layer entry in .kb-config/layers.yaml and can normalize read-only tracker inputs from that layer's connections.trackers[] declarations when legacy roadmap.issue-trackers[] entries are absent.
When to invoke
Invoke whenever the user:
- Types
/kb roadmap(optionally followed by--since,--scope,--workstream,digest,sync). - Asks for a roadmap, status, or deviation report that spans both a planning tool and a repository.
- Asks "what shipped vs. what was planned?", "where does my roadmap drift from reality?", or "which tickets have no code?"
The single command model
One entry point — /kb roadmap — with context-driven subcommands:
| Input | Action |
|---|---|
/kb roadmap |
Generate artifact with default scope + timeframe |
/kb roadmap --since YYYY-MM-DD |
Custom baseline |
/kb roadmap --scope <name> |
Scope to a workstream declared in .kb-config/layers.yaml |
/kb roadmap digest |
Pull latest plan + delivery state; compute delta; do not render |
/kb roadmap sync |
Propose plan-source updates based on delivery reality (dry-run default) |
What ships with it
20 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.
- README.md 2.8 KB
- references/adapters.md 5.8 KB
- references/artifact-contract.md 3.6 KB
- references/audit.md 7.3 KB
- references/authoring-commands.md 12 KB
- references/command-reference.md 8.1 KB
- references/config-schema.md 9.8 KB
- references/correlation-ladder.md 4.2 KB
- references/discuss-mode.md 1.8 KB
- references/folder-layout.md 3.4 KB
- references/html-template.md 7.7 KB
- references/issue-trackers.md 10 KB
- references/journey-grounding.md 7.2 KB
- references/mismatch-findings.md 2.5 KB
- references/phase-gates.md 3.2 KB
- references/state-machine.md 4.4 KB
- scripts/kb_roadmap.py 96 KB runs code
- templates/roadmap.html.hbs 11 KB
- templates/roadmap.json.schema.json 4.3 KB
- templates/roadmap.md.hbs 3.3 KB
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.
- 6d ago Changed · -16 lines ba2ac5990e37
- 1mo ago Changed · +5 lines 2b961a66f12c
- 1mo ago First seen · 264 lines · 84 tokens per session scan A 1cc133ce5ec2
kb-roadmap is a skill published in the GitHub repository wlfghdr/agentic-kb (10 stars, last pushed 6d ago), licensed Apache-2.0. It adds 84 tokens to every session and 4,152 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 2026-08-31.
Other skills, from other repositories
create-issue
Draft and submit a GitHub issue from a user idea or bug description, with bilingual body and correct labels.
awesome-ai-agents-curation
Help founders prepare evidence-backed AI agent project submissions and help maintainers triage project issues and pull requests for the Awesome AI Agents list.
01-sdlc
Orchestrates a request from framing to a draft pull request, autonomous or supervised, isolating implementation, independent review, and final outcome challenge. Use when the user wants to deliver a change end to end. Not for one step.
02-user-stories
Produces or refines ordered User Stories from an Epic, Product Brief, PRD, or bounded request. Use when the user wants to slice, write, assess, order, or persist Stories. Not for Epics or implementation.
07-epic
Produces or refines an outcome-based Epic for a product backlog. Use when the user wants to frame, review, resume, or persist an Epic. Not for Product Briefs, User Stories, or implementation.
09-defect
Produces or refines a backlog Defect from an observed product mismatch. Use when the user wants to report, assess, link, order, transition, or verify a defect. Not for incident response, debugging, or implementation.