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 rpraharaj/forward-deployed-engineer --skill delivery-plangit clone --depth 1 https://github.com/rpraharaj/forward-deployed-engineerWrote 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/rpraharaj/forward-deployed-engineer/delivery-plan)<a href="https://agentmods.dev/skills/rpraharaj/forward-deployed-engineer/delivery-plan"><img src="https://agentmods.dev/badge/skills/rpraharaj/forward-deployed-engineer/delivery-plan/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/rpraharaj/forward-deployed-engineer/delivery-plan"><img src="https://agentmods.dev/badge/skills/rpraharaj/forward-deployed-engineer/delivery-plan.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 | $0.00095 | $0.01979 |
| Opus 5 | $0.00048 | $0.00989 |
| Sonnet 5 | $0.00019 | $0.00396 |
| Haiku 4.5 | $0.00010 | $0.00198 |
Grade A, and why
delivery-plan 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 8d 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 — 168 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Delivery plan
The order of work, and what would change it.
Why this exists
Most plans are sequenced by convenience: easiest first, or in the order the requirements were written. That feels productive and it systematically defers the moment you discover the plan was wrong.
The alternative is to sequence by risk, so the things most likely to invalidate the plan happen first. It feels slower in week one and it is dramatically cheaper, because a plan that breaks in week one can be re-planned while everyone still has options. The same break in week six is a crisis.
For an FDE there's a second reason. Your credibility rests on being predictable. Delivering something small early, then re-planning honestly when a fact changes, builds more trust than a confident plan that holds until it collapses.
When this applies
- Feasibility and estimation exist and someone wants a sequence
- Replanning after a slip or a changed fact
- A plan exists but nobody has said what would invalidate it
- Work spans multiple teams or a release window
When it doesn't
- A single change with no meaningful sequencing decision
- Feasibility hasn't been done — the plan would be fiction
- The question is sizing, not order — that's
estimation
Prerequisites
.fde/04-feasibility.md— shapes, sites, deceptive costs.fde/05b-estimate.md— sizing, if it exists.fde/06-blast-radius-*.md— coordination needs.fde/00b-access.md— blocked access is a dependency with a lead time.fde/08b-change-control.md— the calendar and gates. If missing, offerchange-control-navigation; do not invent CAB dates. If you proceed anyway, every window is[unverified].
Procedure
1. Rank by what could invalidate the plan
For each piece of work, ask: if this goes badly, how much of the rest changes?
Highest-risk-first means putting these early, regardless of size:
- Every
[unverified]item from feasibility - Anything depending on another team's answer or work
- Anything touching a published contract or shared data
- Anything you've never done in this organization — including the first deploy, which is a risk in itself
- Anything with a long lead time, even if it's needed late
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.
- 8d ago First seen · 168 lines · 95 tokens per session scan A 57a0be5492f6
delivery-plan is a skill published in the GitHub repository rpraharaj/forward-deployed-engineer (6 stars, last pushed 21d ago), licensed MIT. It adds 95 tokens to every session and 1,979 once invoked, about $0.0005 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
neat-freak
Knowledge and governance closeout: reconcile project docs, rule files (CLAUDE.md/AGENTS.md), authorized agent memory, and workspace residue with what the code and runtime actually do, so the next session or the next person starts from one current answer. Trigger when the user names "neat-freak", "洁癖", or "/neat" — and…
issue-triage
Triage and categorize GitHub issues with priority labels. Use when user says "triage issues", "check issues", "review open issues", or during regular maintenance of GitHub issue backlog.
feature-dev
Guide a feature implementation through a structured seven-phase workflow with deep codebase understanding, clarifying questions, parallel architecture design, and quality review. Use this skill when the user asks to build a new feature, add functionality, or wants a methodical approach to implementation rather than…
product-manager-toolkit
Use when the user needs product management workflows such as RICE prioritization, customer interview analysis, PRD templates, discovery frameworks, go-to-market strategy, feature prioritization, research synthesis, or requirements documentation.
ijfw-workflow
Use when the user says: 'build', 'create', 'plan', 'new project', 'brainstorm', 'design', 'UI', 'website', 'dashboard', 'app', 'help me build', 'launch', 'book', 'campaign', or anything project-level. Skill body decides Quick vs Deep path.
ijfw-plan
Use when the user says 'plan this', 'plan it', 'make a plan', 'let's plan', 'draft a plan', 'how should we tackle this', 'break this down', or invokes '/ijfw-plan'. Produces a falsifiable PLAN.md (software, book, campaign, design, research) with task breakdown, dependency wave-table, and success criteria — gated by…