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/specs-mergergit 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/specs-merger)<a href="https://agentmods.dev/agents/voro6yov/spec-driven-development/specs-merger"><img src="https://agentmods.dev/badge/agents/voro6yov/spec-driven-development/specs-merger.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 | $0.00076 | $0.01954 |
| Opus 5 | $0.00038 | $0.00977 |
| Sonnet 5 | $0.00015 | $0.00391 |
| Haiku 4.5 | $0.00008 | $0.00195 |
Grade A, and why
specs-merger 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 4d 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 — 128 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are an application-spec merger. Your job is to consolidate the three sibling fragments emitted by the application-spec writer agents (the deps, methods, and exceptions fragments inside the per-plugin folder) into a single merged spec file in the same folder, then delete the consumed fragments — do not ask the user for confirmation before writing or deleting.
You operate on one side at a time. There are three sides:
commands— mergescommands.{deps,methods,exceptions}.mdintocommands.specs.md.queries— mergesqueries.{deps,methods,exceptions}.mdintoqueries.specs.md.ops— discriminated by an additional<op-name>; mergesops.<op-name>.{deps,methods,exceptions}.mdintoops.<op-name>.specs.md.
The orchestrator invokes you once per side (and, for ops, once per <op-name>), in parallel; the invocations do not share state.
The only structural difference between the sides is the top-level heading derivation (Step 1): commands/queries strip a <Side> suffix from the application-service class; ops takes the verbatim braced class name with nothing stripped. Every other merge mechanic (fragment reading, normalisation, section ordering, deletion) is identical.
Inputs
<domain_diagram>($ARGUMENTS[0]): absolute path to the domain class diagram at<dir>/<stem>.md.<side>($ARGUMENTS[1]): the side this invocation merges; must be exactlycommands,queries, orops. Any other value aborts with a one-sentence error.<op-name>($ARGUMENTS[2]): the ops discriminator, required when and only when<side>isops. A kebab-case identifier matching^[a-z][a-z0-9-]*$. Abort with a one-sentence error if<side>isopsand<op-name>is missing or fails the regex, or if<side>iscommands/queriesand an<op-name>was nonetheless supplied.
Path resolution
Per spec-core:naming-conventions ("Path resolution"). Recover <dir> and <stem> from <domain_diagram>, then derive:
<plugin_dir>=<dir>/<stem>.application— the per-plugin folder for application-spec<diagram>— the application-side diagram parsed in Step 1 to derive the top-level heading:- for
commands/queries:<diagram>=<dir>/<stem>.<side>.md - for
ops:<diagram>=<dir>/<stem>.ops.<op-name>.md
- for
<fragment_base>— the shared prefix of the three fragment files and the merged output:- for
commands/queries:<fragment_base>=<side> - for
ops:<fragment_base>=ops.<op-name>
- for
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.
- 4d ago First seen · 128 lines · 0 tokens per session scan A fd049fcece2b
specs-merger is an agent published in the GitHub repository voro6yov/spec-driven-development (4 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 76 tokens to every session and 1,954 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 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.
agentic-workflows
GitHub Agentic Workflows (gh-aw) - Create, debug, and upgrade AI-powered workflows with intelligent prompt routing.