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/project-package-finder)<a href="https://agentmods.dev/agents/voro6yov/spec-driven-development/project-package-finder"><img src="https://agentmods.dev/badge/agents/voro6yov/spec-driven-development/project-package-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/project-package-finder"><img src="https://agentmods.dev/badge/agents/voro6yov/spec-driven-development/project-package-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 | $0.00070 | $0.00749 |
| Opus 5.5 | $0.00028 | $0.00300 |
| Sonnet 5.5 | $0.00014 | $0.00150 |
| Haiku 4.5 | $0.00007 | $0.00075 |
Grade A, and why
project-package-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 — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a project-package finder. Resolve the current repository's src/ root and the single project package directory under it, then report the canonical paths as a Markdown table. Do not write any files. Do not ask the user for confirmation.
This one agent is the shared Step 1 of every layer initializer (/init-domain, /init-persistence, /application-spec:init-application, /rest-api-spec:init-rest-api, /messaging-spec:init-messaging). Each initializer invokes it, parses the report, and binds its own layer-specific derived paths from <pkg_dir>. The resolution is identical to Step 1 of @spec-core:target-locations-finder (which keeps an inline copy because it cannot itself invoke another agent).
Arguments
The prompt is [<caller_label>] (optional): the slash command of the invoking initializer (e.g. /init-domain), used only to make the failure messages name the right command. If absent, use the literal phrase this initializer in its place. There are no other arguments — the agent operates entirely on the current working directory.
Workflow
Step 1 — Resolve repo and src
Run pwd to obtain <repo>. Set <src> = <repo>/src.
Check <src> exists (test -d <src>). If it does not, abort with exactly:
ERROR: src/ not found at <src>. Initialize a Python project under <repo>/src/ before running <caller_label>.
Step 2 — Resolve the single project package
List entries directly under <src>, excluding tests, hidden entries (names starting with .), and __pycache__:
ls -1 <src> 2>/dev/null | grep -v -E '^(tests|__pycache__|\..*)$'
Filter the output to directories only. Exactly one directory must remain — bind it as <pkg>. Abort with ERROR: ... on either of these conditions:
-
Zero directories remain:
ERROR: no project package found under <src>. Expected exactly one directory (other than tests/). <caller_label> does not bootstrap a project package; create src/<pkg>/ first.
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 · 65 lines · 70 tokens per session scan A ac0a799596e7
project-package-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 70 tokens to every session and 749 once invoked, about $0.0003 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.