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 shennawardana23/skillme --skill roadmapping-and-tradeoff-communicationgit clone --depth 1 https://github.com/shennawardana23/skillmeWrote 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/shennawardana23/skillme/roadmapping-and-tradeoff-communication)<a href="https://agentmods.dev/skills/shennawardana23/skillme/roadmapping-and-tradeoff-communication"><img src="https://agentmods.dev/badge/skills/shennawardana23/skillme/roadmapping-and-tradeoff-communication/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/shennawardana23/skillme/roadmapping-and-tradeoff-communication"><img src="https://agentmods.dev/badge/skills/shennawardana23/skillme/roadmapping-and-tradeoff-communication.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 | $0.00113 | $0.01874 |
| Opus 5 | $0.00056 | $0.00937 |
| Sonnet 5 | $0.00023 | $0.00375 |
| Haiku 4.5 | $0.00011 | $0.00187 |
Grade A, and why
roadmapping-and-tradeoff-communication 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 9d 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 — 156 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Roadmapping and Tradeoff Communication
Build roadmaps around outcomes and horizons, not features and dates. Communicate tradeoffs by naming the mechanism that would have to change, not by softening a refusal.
Why date-committed feature roadmaps backfire
A roadmap that lists "Feature X — ships March 15" makes a promise the team usually cannot keep, for reasons that have nothing to do with execution quality: estimates made months out are wrong by construction (unknown unknowns compound over time), priorities shift as the market or the data changes, and the roadmap gets treated as a contract the moment a stakeholder builds their own plan on top of that date. When the date slips — and on any roadmap spanning more than a few weeks, some date will slip — the failure mode isn't the delay itself, it's that stakeholders correctly learn the roadmap's dates were never reliable and stop trusting the next roadmap too. The trust damage compounds across cycles, not just within one.
The deeper problem: a date-committed feature list states false certainty about two things at once — that this specific feature is the right solution (not yet validated), and that it will take exactly this long (not yet known). Bundling an unvalidated solution with a precise date manufactures confidence the underlying work doesn't support.
Now / Next / Later
Popularized by Janna Bastow (co-founder of ProdPad) as a response to the date-driven Gantt roadmap, Now/Next/Later organizes roadmap items into three horizons instead of a calendar:
- Now — actively being worked on. Specific enough to describe concrete scope; confidence is high because it's in progress or fully scoped.
- Next — validated as a priority and coming after Now, but not yet scoped in detail. Sequencing is fairly firm; timing is not.
- Later — directionally important, on the radar, but not yet validated or prioritized against everything else that could land there. Genuinely likely to change.
The horizon itself communicates confidence implicitly, without ever writing a date — an item in "Later" tells the stakeholder "this is a direction we believe in, not a commitment" without saying that sentence out loud every time someone asks. This is the format's real mechanism: it replaces an explicit date (which reads as a promise) with a positional signal (which reads as a confidence level) that degrades gracefully instead of breaking trust when it moves.
What ships with it
3 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.
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.
- 9d ago First seen · 156 lines · 113 tokens per session scan A fcfb87be8403
roadmapping-and-tradeoff-communication is a skill published in the GitHub repository shennawardana23/skillme (2 stars, last pushed 15d ago), licensed Apache-2.0. It adds 113 tokens to every session and 1,874 once invoked, about $0.0006 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 2026-09-03.
Other skills, from other repositories
autonomous-workflow
The phase-based machinery (0–7) behind the aw dispatcher — task intake through tested PR delivery in an isolated Git worktree, with optional companion skills for planning, quality gates, TDD, UX, code quality, docs, and CI verification. Companions skip silently if not installed. NOT the entry point and not…
batch-linear-tickets
Batch-analyze and resolve multiple Linear tickets — bug fixes and feature work. For each ticket: classifies as bug or feature (auto from Linear labels, or via the --type flag), dispatches the appropriate per-ticket analysis (linear-ticket-investigator + rca-investigator for bugs, just linear-ticket-investigator for…
aw
Ships autonomous, end-to-end coding work — implement a feature or fix, all the way to a tested draft PR — from a single opt-in entry point. Detects the task tier (Micro / Lite / Full) and routes: Micro/Lite run single-pass in this context; Full hands off to the aw-planner → aw-executor agents. Use when the user asks…
openspec-implementation
A workflow for implementing an approved technical specification one task at a time. It reads the proposal, makes the changes, runs tests, and validates the result.
codely-plan-create-github
Create a plan for the specified task and store it as GitHub issues in the repository of the current working directory. Given the URL of a GitHub issue, it turns that issue into the parent "plan" issue (Goal, Context and a checklist of phases) and creates one child issue per phase, linking every phase as a native…
codely-plan_phase-implement-github
Implement one phase of a plan stored as GitHub issues in the repository of the current working directory. Given the URL of a phase (child) issue it implements that phase; given the parent plan issue it finds and implements the current phase. Only implements a single phase per invocation, then stops for user review. It…