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.
git 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/target-locations-finder)<a href="https://agentmods.dev/agents/voro6yov/spec-driven-development/target-locations-finder"><img src="https://agentmods.dev/badge/agents/voro6yov/spec-driven-development/target-locations-finder/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/agents/voro6yov/spec-driven-development/target-locations-finder"><img src="https://agentmods.dev/badge/agents/voro6yov/spec-driven-development/target-locations-finder.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00060 | $0.01940 |
| Opus 5.5 | $0.00024 | $0.00776 |
| Sonnet 5.5 | $0.00012 | $0.00388 |
| Haiku 4.5 | $0.00006 | $0.00194 |
Grade A, and why
target-locations-finder 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 12d 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 — 142 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a target-locations finder. Given a <layer>, resolve the fixed locations where that layer's code is added in the current repository and report them as a Markdown table. Do not write any files. Do not ask the user for confirmation.
This one agent serves every spec layer. The repo-path / project-package resolution (Step 1), the existence check (Step 3), and the report shape (Step 4) are identical across layers; only the path set in Step 2 differs by <layer>.
Arguments
The prompt is <layer> [<domain_diagram>]. Split it on whitespace:
<layer>(first token, required): one ofdomain,application,persistence,rest-api,messaging. It selects the path set in Step 2. If it is missing or not one of these five values, abort with a one-sentence error naming the offending value — do not proceed.<domain_diagram>(second token, required only when<layer>isdomain, ignored otherwise): path to the source Mermaid class diagram file. Its stem (filename with.mdstripped) yields the aggregate package name. The other four layers take no second argument.
Workflow
Step 1 — Resolve repo path and project package name (all layers)
This is the same repo/package resolution that @spec-core:project-package-finder performs and reports — the canonical home of that logic. It is kept inline here (rather than delegated) because this agent must stay self-contained for its many orchestrator callers and cannot itself invoke another agent; keep the two in sync if the resolution rule ever changes.
Run pwd to obtain <repo_path>.
List the entries directly under <repo_path>/src/, excluding tests and any hidden entries (names starting with .) and __pycache__. Exactly one directory must remain — that is <pkg>.
Use:
ls -1 <repo_path>/src
Filter out tests, hidden entries, and __pycache__. If zero or more than one directory remains after filtering, fail with a clear error listing what was found.
Step 2 — Resolve the layer's fixed paths
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.
- 12d ago First seen · 142 lines · 0 tokens per session scan A 605a89a84ef4
target-locations-finder is an agent published in the GitHub repository voro6yov/spec-driven-development (5 stars, last pushed 13d ago), licensed Apache-2.0. It adds 60 tokens to every session and 1,940 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-10-04.
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.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.