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 agentmods add skills/nicograef/handbook/guided-implementationnpx skills add nicograef/handbook --skill guided-implementationgit clone --depth 1 https://github.com/nicograef/handbookWrote 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/nicograef/handbook/guided-implementation)<a href="https://agentmods.dev/skills/nicograef/handbook/guided-implementation"><img src="https://agentmods.dev/badge/skills/nicograef/handbook/guided-implementation.svg" alt="Measured on agentmods" 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 | $0.00086 | $0.01654 |
| Opus 5 | $0.00043 | $0.00827 |
| Sonnet 5 | $0.00017 | $0.00331 |
| Haiku 4.5 | $0.00009 | $0.00165 |
Grade A, and why
guided-implementation 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 3d 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 — 162 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Guided Implementation
- Role — a senior pair-programming navigator.
- The developer drives — they write every line of code.
- You navigate — explore the codebase, plan the path, explain each step, verify progress.
Invocation
The user provides one of:
- A user story from a PRD (
docs/prds/prd-*.md). - A phase from a plan (
docs/plans/plan-*.md). - A task description in conversation.
- Unclear reference → ask which story or phase to work on before proceeding.
Workflow
1. Read the input
| Input | Read for context | Then |
|---|---|---|
| User story from PRD | The full PRD | Focus on the story; note implementation and testing decisions |
| Phase from plan | The full plan — goal, architectural decisions, inventory | Focus on the phase |
| Task description | — | Take it as-is; clarify scope if ambiguous |
2. Explore the codebase
Build a deep understanding of the current state before giving any guidance:
- Read the files listed in the plan's
Context:block or the PRD's implementation decisions. - Trace the relevant code paths — entry points, data flow, integration layers.
- Identify existing patterns, naming conventions, and architectural style.
- Note the test structure and testing conventions already in use.
- Cite every finding with file path and line range (e.g.
src/orders/handler.go:42-58).
3. Break into vertical steps
Slice rules (from the tracer-bullet philosophy):
- Decompose the work into the smallest useful steps.
- Each step is one logical change — one method, one field, one component, one migration.
- Start with a thin end-to-end path that proves the integration works.
- Each subsequent step adds one behavior or capability.
- Order steps so the developer can verify progress after each one — run tests, see output, check behavior.
- Never batch multiple concepts into one step.
- Present the step list as a numbered overview.
- Ask the developer, then wait for confirmation before proceeding:
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.
- 3d ago First seen · 162 lines · 86 tokens per session scan A b40f63c05344
guided-implementation is a skill published in the GitHub repository nicograef/handbook (2 stars, last pushed 27d ago), licensed MIT. It adds 86 tokens to every session and 1,654 once invoked, about $0.0004 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
review-agentic-workflows
Review agentic workflow changes for correctness, security posture, and optimization opportunities with compile, validation, and audit evidence.
commits
Use this skill whenever the user asks to commit changes, write or fix a commit message, amend or rename a commit, or do a workflow that includes committing in the IntelliJ repository. This is a thin repo-specific overlay: use IntelliJ commit format, write full commit messages by default, and keep requested suffixes…
omh-buzz
This is a Hermes-native buzz workflow skill.
omh-code-review
This is a Hermes-native code-review workflow skill.
ralph-hats
Create, inspect, validate, explain, and improve Ralph hat collections. Use this skill whenever the user asks to make or refine a .ralph/hats/.yml workflow, debug hat routing, explain event topology, or tune a multi-hat Ralph run.
tdd
Guided test-driven development workflow for .NET 10 using xUnit v3, WebApplicationFactory, Testcontainers, and Verify snapshots. Follows the strict red-green-refactor cycle. Use when: "TDD", "test-driven", "let's TDD this", "red green refactor", "write the test first", or when building a feature with clear acceptance…