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 skills/ronronner02/codepilot-agent/spec-povnpx skills add ronronner02/codepilot-agent --skill spec-povgit clone --depth 1 https://github.com/ronronner02/codepilot-agentWrote 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/ronronner02/codepilot-agent/spec-pov)<a href="https://agentmods.dev/skills/ronronner02/codepilot-agent/spec-pov"><img src="https://agentmods.dev/badge/skills/ronronner02/codepilot-agent/spec-pov.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 | $0.00114 | $0.03937 |
| Opus 5 | $0.00057 | $0.01969 |
| Sonnet 5 | $0.00023 | $0.00787 |
| Haiku 4.5 | $0.00011 | $0.00394 |
Grade B, and why
spec-pov scanned grade B with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
chmod 700 "$SCRATCH_DIR" How it starts
The opening of the file, as written. The whole thing — 138 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Form a Point of View
Return a decisive, graded verdict on something from the outside world — judged against this project, not in the abstract.
Use the user's current request from the conversation as the POV input.
Note: Use the current date from the active host context. Use this when weighting external sources and dating artifacts.
The one rule that is the whole moat
Do not issue a verdict you did not earn against the project's own context. Generic web research already covers "tell me about X"; the differentiator is never "research the web" — it is the refusal to answer in the abstract. The verdict must clear two absolute floors (see references/method.md): a project floor (a concrete verified project fact — a named incumbent + a touchpoint, or for a net-new adoption the verified absence of one plus where it would fit, or a prior decision) and an external floor (at least one verified external source). The floors are absolute and independent — strong external evidence never compensates for a thin project leg, and vice versa. Neither the conversation nor the user's own assertions substitute for grounding.
Interaction Method
When you must ask the user a question, use the platform's blocking question tool: AskUserQuestion in Claude Code (call ToolSearch with select:AskUserQuestion first if its schema isn't loaded), request_user_input in Codex. Fall back to numbered options in chat only when no blocking tool exists in the harness or the call errors (e.g., Codex edit modes) — not because a schema load is required. Never silently skip the question. Ask one question at a time.
Model Tiers
Dispatch is tiered by task shape, never hardcoded to a model name:
- Extraction tier — the project-grounding scout and the precedent-&-activity scout: search-and-quote work. Request the cheapest capable tier only when
worker_model_override: supported; otherwise inherit. - Generation tier — the external-evidence researcher: web/docs retrieval and entailment checking. Request the balanced mid-tier only when
worker_model_override: supported; otherwise inherit. - Ceiling tier — the verdict reasoning itself (the two-floor gate, the skeptic synthesis, the verdict contract). This runs in the main conversation on the orchestrator's model; nothing is dispatched for it.
What ships with it
13 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- references/agents/external-evidence-researcher.md 2.5 KB
- references/agents/pov-peer.md 2.2 KB
- references/agents/precedent-activity-scout.md 2.9 KB
- references/agents/project-grounding-scout.md 4.5 KB
- references/boundaries.md 2.8 KB
- references/cross-model-panel.md 3.4 KB
- references/intake.md 3.8 KB
- references/invocation.md 3.0 KB
- references/method.md 5.8 KB
- references/pov-schema.json 1.7 KB
- references/report.md 1.7 KB
- scripts/cross-model-pov.sh 8.6 KB runs code
- scripts/peer-job-runner.py 86 KB runs code
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.
- 3d ago First seen · 138 lines · 114 tokens per session scan B d1efe4d5a01e
spec-pov is a skill published in the GitHub repository ronronner02/codepilot-agent (0 stars, last pushed 2d ago), licensed MIT. It adds 114 tokens to every session and 3,937 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it B with 1 finding (asks for root). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
rag-governance
Implement access-aware RAG in Enterprise RAG or VAP: hybrid retrieval, rerank, citations, AegisAI HITL for sensitive chunks. Use when tuning retrieval, adding Qdrant adapter, or wiring enterpriseragplatform.
governed-ai-stack
Maps tasks to the vpeetla-ai 6-layer reference stack (VAP, AegisAI, Enterprise RAG, AegisLoop, Content Factory, LoopForge). Use when choosing which repo to change, designing integrations, or explaining architecture.
loop-engineering
Implement ODAEU harness loops, RAG evolve tuning, and procedural memory in LoopForge or similar systems. Use when building self-improving agents, eval gates, MCP tool bridges, or RAG version trees.
mcp-apps-builder
MANDATORY for ALL MCP server work - mcp-use framework best practices and patterns. READ THIS FIRST before any MCP server work, including: Creating new MCP servers Modifying existing MCP servers (adding/updating tools, resources, prompts, widgets) Debugging MCP server issues or errors Reviewing MCP server code for…
project-graveyard
Scans the developer's machine for dead side projects, autopsies each one from its git history (died at the payments wall, killed by a newer project, finished but never shipped), surfaces their personal death patterns, and picks the corpse most worth resurrecting — then helps ship it. Use when the user mentions…
dependency-doctor
Checks requirements.txt, pyproject.toml, and package.json dependency manifests for surface-level direct-dependency footguns: standard-library shadowing pins, abandoned backports, unpinned dependencies, and obvious intra-manifest conflicts, plus opt-in PyPI yanked releases. Use when the user asks to check a manifest…