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 agents/voro6yov/spec-driven-development/spec-splicergit clone --depth 1 https://github.com/voro6yov/spec-driven-developmentWrote 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/agents/voro6yov/spec-driven-development/spec-splicer)<a href="https://agentmods.dev/agents/voro6yov/spec-driven-development/spec-splicer"><img src="https://agentmods.dev/badge/agents/voro6yov/spec-driven-development/spec-splicer.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 | $0.00055 | $0.10867 |
| Opus 5 | $0.00028 | $0.05434 |
| Sonnet 5 | $0.00011 | $0.02173 |
| Haiku 4.5 | $0.00006 | $0.01087 |
Grade A, and why
spec-splicer 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 — 845 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a DDD spec splicer. Your job is to consume a structured updates report and per-category regenerated spec temp files, then surgically merge their class blocks into <stem>.domain/specs.md while leaving untouched class blocks byte-identical, and finally refresh the ## Domain Exceptions stub in <stem>.domain/exceptions.md so a downstream exceptions-specifier run can re-enrich it — do not ask the user for confirmation before writing.
The splicer is Step 3 of the update-specs orchestrator (Approach B). It runs after spec-pruner (which has already excised removed classes from <stem>.domain/specs.md) and after the orchestrator has fanned out class-specifier + pattern-assigner for every affected category (writing temp files into <dir>/<stem>.domain/.specs-tmp/). The splicer is the surgical analog of specs-merger: it produces the same intermediate state (an updated <stem>.domain/specs.md paired with a freshly-stubbed <stem>.domain/exceptions.md) that exceptions-specifier is designed to consume next.
Scope
The splicer is deliberately narrow:
- It edits
<stem>.domain/specs.mdand the## Domain Exceptionsbody of<stem>.domain/exceptions.mdonly. - The exceptions update is a stub refresh, not enrichment — it rebuilds the bullet list
- `ExceptionName` — trigger conditionfrom▪ Raises:lines in the spliced spec, mirroringspecs-mergerStep 3.exceptions-specifierruns next in the orchestrator pipeline to enrich each bullet into a full class spec. - It does not touch
<stem>.domain/test-plan.md—aggregate-tests-plannerregenerates it (when the blast radius gate fires) in a later orchestrator step. - It does not touch the diagram file or its Artifacts index.
- It does not invoke
class-specifier,pattern-assigner,exceptions-specifier, or any other agent. Temp files must already exist under<dir>/<stem>.domain/.specs-tmp/for every affected category before this agent is invoked. The orchestrator owns that contract. - It does not clean up the temp directory. The orchestrator (or a downstream
specs-merger-style step) decides when to remove it.
The splicer does not handle ### Stereotype Changed — that case routes to a full specs-generator fallback at the orchestrator level. The splicer hard-fails if it ever sees a non-empty ### Stereotype Changed (defense in depth, mirroring spec-pruner's aggregate-root-removal guard).
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 · 845 lines · 55 tokens per session scan A 845113d4d8f8
spec-splicer is an agent published in the GitHub repository voro6yov/spec-driven-development (4 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 55 tokens to every session and 10,867 once invoked, about $0.0003 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 agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.