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 skills add rp1-run/rp1 --skill project-birds-eye-viewgit clone --depth 1 https://github.com/rp1-run/rp1Wrote 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/skills/rp1-run/rp1/project-birds-eye-view)<a href="https://agentmods.dev/skills/rp1-run/rp1/project-birds-eye-view"><img src="https://agentmods.dev/badge/skills/rp1-run/rp1/project-birds-eye-view/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/skills/rp1-run/rp1/project-birds-eye-view"><img src="https://agentmods.dev/badge/skills/rp1-run/rp1/project-birds-eye-view.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00044 | $0.01184 |
| Opus 5 | $0.00022 | $0.00592 |
| Sonnet 5 | $0.00009 | $0.00237 |
| Haiku 4.5 | $0.00004 | $0.00118 |
Grade A, and why
project-birds-eye-view 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 — 120 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Project Bird's-Eye View Generator
ROLE: Workflow dispatcher. Bootstraps run tracking, spawns the project-documenter sub-agent, registers the produced artifact in Arcade. MUST NOT read/write project files or produce documentation content directly.
STATE-MACHINE
stateDiagram-v2
[*] --> load_kb
load_kb --> analyse : kb_ready
analyse --> generate : analysis_complete
generate --> validate_diagrams : document_written
validate_diagrams --> [*] : done
On each phase transition, emit:
rp1 agent-tools emit --harness $CURRENT_HOST \
--workflow project-birds-eye-view \
--type status_change \
--run-id {RUN_ID} \
--name "Bird's-eye view: {RUN_NAME}" \
--step {CURRENT_STATE} \
--data '{"status": "running"}'
RUN_NAME is resolved once, up front, from basename {projectRoot} — it is stable before the sub-agent runs, so every emit (including the first) can carry it. The sub-agent's resolved PROJECT_SLUG is used for the artifact filename, not the run name.
Terminal state validate_diagrams uses --data '{"status": "completed"}' and --close-run.
Governance
Role: workflow dispatcher.
Scope limits: dispatch only — MUST NOT read/write project files or generate documentation content. Sub-agent handles all content work.
Error degradation: missing KB dir → warn user to run /knowledge-build, emit status_change with {"status":"failed","reason":"kb_missing"}, STOP. Sub-agent failure → propagate error, emit failure status, STOP. No retry loops.
Transition guards: state-machine transitions emitted per STATE-MACHINE; RUN_ID mandatory on every emit.
Dispatch
- Resolve
RUN_NAME=basename {projectRoot}. - Emit entry into
load_kbwith{"status":"running"}. Verify{kbRoot}exists — if not, emit{"status":"failed","reason":"kb_missing"}and STOP. - Emit entry into
analysewith{"status":"running"}— this is the state the sub-agent runs in. - Invoke the project-documenter agent:
{% dispatch_agent "rp1-base:project-documenter" %} PROJECT_CONTEXT: {PROJECT_CONTEXT} FOCUS_AREAS: {FOCUS_AREAS} KB_ROOT: {kbRoot} WORK_ROOT: {workRoot} PROJECT_ROOT: {projectRoot} CODE_ROOT: {codeRoot} RUN_ID: {RUN_ID} {% enddispatch_agent %}
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 · 120 lines · 44 tokens per session scan A 26c4ca158507
project-birds-eye-view is a skill published in the GitHub repository rp1-run/rp1 (38 stars, last pushed 4d ago), licensed Apache-2.0. It adds 44 tokens to every session and 1,184 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 2026-08-30.
Other skills, from other repositories
skill-curator
A Chinese-language evaluator for deciding whether developer tools and agent resources are suitable for a curated collection. It checks real repositories, installation paths, activity, duplicates, and security boundaries using evidence.
git-workflow
A guide for handling Git repository work safely, including status checks, branches, commits, pushes, pull requests, and rebasing. Git is a version-control system that records code changes and coordinates work between developers.
i18n-helper
A helper for adding internationalization, which lets software show different languages and regional text. It finds user-visible text written directly in code and moves it into language files.
brainstorm
Explore ambiguous or early-stage ideas interactively — tracks wish-readiness and crystallizes into a design for wish.
refactor-advisor
A code review helper that finds common design and maintenance problems in a codebase and suggests ways to restructure the code.
acceptance-test-authoring
Use when creating or modifying acceptance tests, configuring cucumber-js or behave runners, writing or refactoring step definitions, linting executable Gherkin specs, choosing an acceptance stack, or implementing OpenSpec tasks that involve acceptance tests.