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/mattgierhart/prd-driven-context-engineering/prd-v07-implementation-loopnpx skills add mattgierhart/PRD-driven-context-engineering --skill prd-v07-implementation-loopgit clone --depth 1 https://github.com/mattgierhart/PRD-driven-context-engineeringWrote 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/mattgierhart/prd-driven-context-engineering/prd-v07-implementation-loop)<a href="https://agentmods.dev/skills/mattgierhart/prd-driven-context-engineering/prd-v07-implementation-loop"><img src="https://agentmods.dev/badge/skills/mattgierhart/prd-driven-context-engineering/prd-v07-implementation-loop.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 | $0.00113 | $0.04774 |
| Opus 5 | $0.00056 | $0.02387 |
| Sonnet 5 | $0.00023 | $0.00955 |
| Haiku 4.5 | $0.00011 | $0.00477 |
Grade A, and why
prd-v07-implementation-loop 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 5d 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 — 459 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Implementation Loop
Position in workflow: v0.7 Test Planning → v0.7 Implementation Loop → v0.8 Release
Consumes
This skill requires prior work from v0.7 Epic Scoping and v0.7 Test Planning:
- EPIC-* entries (from v0.7 Epic Scoping) — EPIC context, objectives, Context & IDs table, execution plan phases, Session State tracking
- TEST-* test specifications (from v0.7 Test Planning) — Acceptance criteria in Given-When-Then format; tests define "done" for each deliverable
- API-* endpoint contracts (referenced in EPIC Context & IDs) — Implementation targets with request/response shapes, error codes, constraints
- DBT-* schema specifications (referenced in EPIC Context & IDs) — Data model, field types, relationships, constraints to implement
- BR-* business rules (referenced in EPIC Context & IDs) — Product logic constraints to enforce in code
- Existing SoT files (if brownfield) — Durable specs that guide implementation without re-research
This skill assumes EPIC- and TEST- entries are complete, with all upstream IDs fully specified.
Produces
This skill updates/creates:
- Working code (implementation of API-, DBT-, BR-, tested against TEST-) — Runnable code with @implements tags tracing back to specifications; passes all TEST- for EPIC
- Updated SoT entries (if implementation reveals changes) — When building reveals new constraints or edge cases, update API-/DBT-/BR- entries immediately (not deferred)
- Session State updates (EPIC.md Section 1) — "Brain dump" tracking exact stopping point, Next Steps for resume, blockers, decisions, Context
- Development Graph (
status/devgraph.json) — the@implements/@verifiestags you write are harvested into bridge edges, producing the as-built layer that readiness scores (implementation_coverage,architecture_conformance) and the HeartBeat visualizer renders. Schema:docs/DEVELOPMENT_GRAPH.md.
All implementation outputs are code and live SoT, not confidence-based. They are:
- Traceable (every function tagged with @implements pointing to specification ID)
- Tested (all TEST- for EPIC pass before marking phase/EPIC complete)
- SoT-synchronized (implementation matches specs/ or specs/ updated to match implementation reality)
- Session-state-preserved (Session State section allows seamless resume from exact stopping point)
What ships with it
6 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.
- 5d ago First seen · 459 lines · 113 tokens per session scan A 1def7f2dcb64
prd-v07-implementation-loop is a skill published in the GitHub repository mattgierhart/PRD-driven-context-engineering (182 stars, last pushed 4d ago), licensed MIT. It adds 113 tokens to every session and 4,774 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 2026-08-30.
Other skills, from other repositories
ralplan
Consensus planning entrypoint that auto-gates vague ralph/autopilot/team requests before execution.
remember
Review reusable project knowledge and decide what belongs in project memory, notepad, or durable docs.
embedding-strategies
Select and optimize embedding models for semantic search and RAG applications. Use when choosing embedding models, implementing chunking strategies, or optimizing embedding quality for specific domains.
docx-comment-reply
Reply to comments (批注) in Word .docx/.doc files: extract comment context, draft replies, write threaded replies back, and validate OOXML.
oma-scholar
Scholarly research companion using Knows sidecar spec (.knows.yaml). Generates, validates, reviews, queries, and compares structured research-paper sidecars, and fetches them from knows.academy. Use for academic literature search, survey synthesis, paper authoring assistance, and peer review with token-efficient…
oma-hwp
Convert HWP / HWPX / HWPML files to Markdown using kordoc. Extracts text, headings, tables, lists, images, footnotes, and hyperlinks. Use for Korean word processor files (Hangul), government documents, and AI-ready data preparation.