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 magnus919/agent-skills --skill forward-deployed-engineeringgit clone --depth 1 https://github.com/magnus919/agent-skillsWrote 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/magnus919/agent-skills/forward-deployed-engineering)<a href="https://agentmods.dev/skills/magnus919/agent-skills/forward-deployed-engineering"><img src="https://agentmods.dev/badge/skills/magnus919/agent-skills/forward-deployed-engineering/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/magnus919/agent-skills/forward-deployed-engineering"><img src="https://agentmods.dev/badge/skills/magnus919/agent-skills/forward-deployed-engineering.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00105 | $0.02326 |
| Opus 5 | $0.00053 | $0.01163 |
| Sonnet 5 | $0.00021 | $0.00465 |
| Haiku 4.5 | $0.00011 | $0.00233 |
Grade A, and why
forward-deployed-engineering 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 — 159 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Forward-Deployed Engineering
Use this bundle when the work is an embedded technical engagement whose success depends on continuity, not merely a recommendation or a code change. This is a normative operating model synthesized from the role observations in source-index.md and from routed specialist methods; the nine-stage sequence is not an externally standardized methodology.
Lifecycle
Discover → Frame → Hypothesize → Build → Evaluate → Deploy → Adopt → Measure → Generalize
| Stage | Required question | Minimum output | Stop condition |
|---|---|---|---|
| Discover | What user workflow and problem are real? | Stakeholder/workflow map and unknowns | No recognizable problem or access to the relevant workflow |
| Frame | What is in scope, who decides, and what outcome matters? | Engagement charter and assumptions/decisions/risks ledger | Authority, constraints, or outcome cannot be named |
| Hypothesize | What smallest intervention could change the workflow? | Testable hypothesis and decision rule | No falsifiable hypothesis or unsafe test |
| Build | What operationally complete slice can be built? | Thin-slice implementation plan and owner | Dependencies or permissions are infeasible |
| Evaluate | What evidence supports quality, safety, and usefulness? | Evaluation and release decision | Baseline, representative evidence, or risk constraints missing |
| Deploy | Can it be released, recovered, and verified in the authorized environment? | Readiness, rollout, rollback, and verification record | No authorized access, rollback, or release decision |
| Adopt | Do intended users activate and use it in the target workflow? | Adoption scorecard and intervention record | Adoption failure is unexplained or ownership/support is absent |
| Measure | Did the capability change the agreed outcome? | Outcome measurement record | Instrumentation cannot distinguish expected from observed |
| Generalize | What should happen to the local learning? | Productization record and field-learning record | No evidence or receiving owner for the proposed next step |
What ships with it
23 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.
- AGENTS.md 993 B
- evals/evals.json 14 KB
- manifest.yaml 14 KB
- README.md 3.6 KB
- references/adoption-and-measurement.md 1.6 KB
- references/authority-and-escalation.md 2.0 KB
- references/communication.md 1.8 KB
- references/discovery-brief.md 4.3 KB
- references/generalization-and-productization.md 1.9 KB
- references/lifecycle-and-artifacts.md 1.1 KB
- references/route-selection.md 6.7 KB
- references/source-index.md 2.8 KB
- references/worked-example-engagement.md 6.5 KB
- templates/adoption-scorecard.md 606 B
- templates/assumptions-decisions-risks-ledger.md 634 B
- templates/engagement-charter.md 682 B
- templates/engagement-status.md 451 B
- templates/evaluation-and-release-decision.md 551 B
- templates/field-learning-record.md 516 B
- templates/outcome-measurement-record.md 523 B
- templates/productization-record.md 605 B
- templates/stage-handoff-record.md 426 B
- templates/stakeholder-workflow-map.md 504 B
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 · 159 lines · 105 tokens per session scan A e302cf769372
forward-deployed-engineering is a skill published in the GitHub repository magnus919/agent-skills (75 stars, last pushed today), licensed MIT. It adds 105 tokens to every session and 2,326 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 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…