Borrowing it
Nothing to install: this file belongs to pvliesdonk/scholar-mcp. 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/pvliesdonk/scholar-mcp/main/.agents/skills/roadmapping/SKILL.mdgit clone --depth 1 https://github.com/pvliesdonk/scholar-mcpWrote 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/pvliesdonk/scholar-mcp/roadmapping)<a href="https://agentmods.dev/skills/pvliesdonk/scholar-mcp/roadmapping"><img src="https://agentmods.dev/badge/skills/pvliesdonk/scholar-mcp/roadmapping/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/pvliesdonk/scholar-mcp/roadmapping"><img src="https://agentmods.dev/badge/skills/pvliesdonk/scholar-mcp/roadmapping.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 | $0.00059 | $0.04344 |
| Opus 5.5 | $0.00024 | $0.01738 |
| Sonnet 5.5 | $0.00012 | $0.00869 |
| Haiku 4.5 | $0.00006 | $0.00434 |
Grade A, and why
roadmapping 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 23d 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.
This is a copy
100% identical to roadmapping — 5 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 390 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Roadmapping
A roadmap answers three questions: which direction, in what order, and what we do not yet know. It does not answer how. The moment it starts answering how, it has stopped being a roadmap and has become a plan that will be wrong.
Planning skills have one resolution setting. Point them at six months of work and they produce file paths and schemas for things nobody has looked at yet; reviewers then correctly attack that precision and the whole artefact loses credibility. The fix is to plan at a declared resolution and defend it.
The evidence rule
If you do not have hard evidence, you cannot be certain. It is not your job to obtain that evidence during charting.
An explicit request to research or implement authorizes that work. This rule prevents silently turning a roadmap pass into an investigation; it does not override the user's scope or previously authorized work.
Both halves matter. When you reach a gap, the tempting move is to read the code or open five files until you can say something concrete. Do not. That is how a roadmap fills with confident detail about work nobody has scoped.
Assert it, or file it as a known unknown. Never research to promote it.
Every unknown gets a resolved by pointer: which piece of work, when finished, answers it. When nothing planned will answer it and not knowing changes what you do next, the finding out is itself work: file a research issue (see Everything is work). The evidence rule defers research; it does not cancel it.
The model
Three GitHub objects and one document, each holding one kind of fact. This is the fleet-wide definition; the words mean nothing else here.
| Object | Is | Holds |
|---|---|---|
| Epic | a parent issue with native sub-issues, labelled epic |
the story, its frozen outcome ("Done when"), its children, its refinement issue |
| Package | a milestone titled NNN <content-name> |
the payload of exactly one release cut |
| Issue | a feature, bug, research spike or refinement task, labelled by kind | executable work, at whatever resolution it has earned |
| Index | docs/design/roadmap.md |
the argument: why this direction, why this order, what we do not know |
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.
- 23d ago Changed · +4 lines ddbd494edd00
- 1mo ago First seen · 386 lines · 59 tokens per session scan A 5648dba5dc2f
roadmapping is a skill published in the GitHub repository pvliesdonk/scholar-mcp (2 stars, last pushed yesterday), licensed MIT. It adds 59 tokens to every session and 4,344 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 100% identical to roadmapping, differing in 5 lines, and is treated as a copy.
Other skills, from other repositories
servicenow-cmdb
Auditing the CMDB as a data model: CI class hierarchy, raw relationships, CMDB health scorecards, data quality (duplicates, orphans, staleness, missing fields) and CSDM 5 conformance. Use when the user mentions CMDB health, CMDB audit, data quality, duplicates, orphaned or stale CIs, CI classes, relationships in…
exploring-tables
Exploring any ServiceNow table: schema, field types, sample records, relationships, data patterns, a record's history (work notes, comments, field changes), and what touches a table or field (business rules, client scripts, UI policies, ACLs, script includes). Use when the user mentions tables, schemas, fields, data…
triaging-incidents
Creating, triaging, updating, and analyzing ServiceNow incidents, including trend reports. Assess severity, check affected CIs, find related incidents, and recommend assignments. Use when the user mentions incidents, INC numbers, outages, service disruptions, ticket creation, triage, priority, severity, ITSM…
analyzing-access
Reviewing who holds which ServiceNow roles and explaining access denials. Lists admin and securityadmin holders, roles granted directly instead of through groups, roles left on inactive or long-absent users, and diagnoses 401/403 errors, empty results and missing fields. Joins users, groups and roles through…
reviewing-update-sets
Reviewing, analyzing, and comparing ServiceNow update sets before promotion, singly or in batches. Shows changes, risks, dependencies, and conflicts. Use when the user mentions update sets, customizations, promotion, code review, change tracking, pre-deployment review, sysupdatexml, customer updates, 'what changed in…
assessing-change-impact
Assessing what a ServiceNow change request touched and what followed it: affected CIs, other changes on the same CIs in an overlapping window, and incidents on those CIs after the change, without trusting hidden incident-to-change links. Use this skill whenever the user asks whether a change (a CHG number) caused or…