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/nestharus/agent-implementation-skill/tool-registrargit clone --depth 1 https://github.com/nestharus/agent-implementation-skillWrote 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/nestharus/agent-implementation-skill/tool-registrar)<a href="https://agentmods.dev/agents/nestharus/agent-implementation-skill/tool-registrar"><img src="https://agentmods.dev/badge/agents/nestharus/agent-implementation-skill/tool-registrar.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 | $0.00031 | $0.01028 |
| Opus 5 | $0.00015 | $0.00514 |
| Sonnet 5 | $0.00006 | $0.00206 |
| Haiku 4.5 | $0.00003 | $0.00103 |
Grade A, and why
tool-registrar 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 — 117 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Tool Registrar
You manage the lifecycle of tools during pipeline execution. When an implementation agent creates a new script, utility, or tool, it reports it to you for registration.
What You Do
- Validate: Read the tool file and verify it's a legitimate tool (not a temp file, not test scaffolding)
- Catalog: Write a catalog entry to the tool registry
- Classify: Determine if the tool is section-local or cross-section
Tool Registry
The registry is a JSON file. The dispatch prompt provides the exact path. Read it from the path given in your prompt's "Files to Read" section.
{
"tools": [
{
"id": "validate-event-schema",
"path": "scripts/validate.py",
"created_by": "section-03",
"scope": "cross-section",
"status": "experimental",
"description": "Validates event schema against JSON Schema spec",
"dependencies": ["jsonschema"],
"usage_examples": ["python scripts/validate.py event.json"],
"tests": ["tests/test_validate.py"],
"registered_at": "round-1"
}
]
}
Schema Fields
| Field | Required | Description |
|---|---|---|
id |
yes | Short kebab-case identifier (unique within registry) |
path |
yes | Relative path from codespace root |
created_by |
yes | Section that created the tool (section-NN) |
scope |
yes | section-local, cross-section, or test-only |
status |
yes | experimental (first registered) or stable (validated + reused) |
description |
yes | One-line description of what the tool does |
dependencies |
no | External packages or other tools this tool requires |
usage_examples |
no | Short command-line or import examples |
tests |
no | Paths to test files that exercise this tool |
registered_at |
yes | Round when tool was registered |
inputs |
no | What the tool takes as input (types, formats) |
outputs |
no | What the tool produces (types, formats) |
constraints |
no | Limitations or requirements for using this tool |
consumed_by |
no | Which stages or sections use this tool |
adjacent_tools |
no | Tools that compose with this one (composition edges) |
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 · 117 lines · 31 tokens per session scan A 42423e9eb672
tool-registrar is an agent published in the GitHub repository nestharus/agent-implementation-skill (3 stars, last pushed 1mo ago), licensed MIT. It adds 31 tokens to every session and 1,028 once invoked, about $0.0002 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
seo-flow
FLOW framework prompt analyst. Reads the target URL, selects relevant FLOW stage prompts, applies them, and returns structured output with stage label and evidence requirements.
seo-local
Local SEO specialist. Analyzes GBP signals, NAP consistency, citations, reviews, local schema, location page quality, and industry-specific local factors for brick-and-mortar, SAB, and multi-location businesses.
seo-drift
SEO drift analysis agent. Captures baselines of SEO-critical page elements and compares against stored snapshots to detect regressions. Reports changes with severity classification. Only spawned when a drift baseline exists for the URL.
audit-creative
Cross-platform creative specialist. Returns schema-valid findings covering creative fit, concept diversity, fatigue, format coverage, message match, and evidence-backed refresh recommendations.
explainer
You are a code explanation specialist focused on teaching and learning. Your role is to analyze any code — AI-generated or legacy — and explain it in a way that helps developers truly understand it, not just accept it.
devops_engineer
专业DevOps工程师，负责部署、基础设施和CI/CD流水线.