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 allemaar/open-skills --skill plan-deep-divegit clone --depth 1 https://github.com/allemaar/open-skillsWrote 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/allemaar/open-skills/plan-deep-dive)<a href="https://agentmods.dev/skills/allemaar/open-skills/plan-deep-dive"><img src="https://agentmods.dev/badge/skills/allemaar/open-skills/plan-deep-dive/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/allemaar/open-skills/plan-deep-dive"><img src="https://agentmods.dev/badge/skills/allemaar/open-skills/plan-deep-dive.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 | $0.00106 | $0.01801 |
| Opus 5 | $0.00053 | $0.00901 |
| Sonnet 5 | $0.00021 | $0.00360 |
| Haiku 4.5 | $0.00011 | $0.00180 |
Grade A, and why
plan-deep-dive 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 10d 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 — 141 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/deep-dive
Phase-by-phase deep inspection of any multi-phase plan. Stop at each phase, assess completeness, quality, and future-readiness before moving on.
Structured execution spec:
protocol.yon. Read it for the canonical rules and step sequence; this file is explanation. The two must stay in sync — if you edit one, update the other and refresh the@STAMPdate.
Caller Options. Before executing, run the Caller Options protocol (
caller-options/SKILL.md): triage this invocation for material optionality across the venues declared in front-matter; if one path clearly dominates, proceed silently; otherwise surface the options. For very long plans,delegatedkeeps the main context clean while a sub-agent walks the phases and returns the verdict log.
Iterative Depth Protocol.
/plan-createproduces the plan./plan-deep-divepressure-tests it phase by phase. Never batch or skip phases — the value is in the forced stops.
When to escalate to plan-create
If phase-by-phase inspection surfaces gaps that would require redesigning the plan rather than tweaking it (missing phase, wrong sequencing, fundamental approach issue), stop the deep-dive and recommend /plan-create to redesign.
Phase 1 — Load & Enumerate
Identify the active plan. Load implementation_plan.md, PLAN.md, or the current multi-phase artifact (e.g. a multi-phase plan presented inline in the conversation, or a plan document at any path the user has referenced). Extract the ordered list of phases.
Verification step: before entering Phase 2, present the loaded artifact's title and first substantive line to the user and ask: "Is this the correct and current plan?" Do not proceed until confirmed.
Gate: no phases found → cannot proceed.
Phase 2 — Iterative Phase Drill-Down
For each phase, execute the full drill-down loop below. Do NOT advance until the current phase passes all checks.
Running verdict log: maintain a verdict table updated after each Step 5. This log is cited verbatim in Phase 3 — do not reconstruct from memory.
What ships with it
1 file 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.
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.
- 10d ago First seen · 141 lines · 106 tokens per session scan A d2f0b58b9e08
plan-deep-dive is a skill published in the GitHub repository allemaar/open-skills (14 stars, last pushed 23d ago), licensed Apache-2.0. It adds 106 tokens to every session and 1,801 once invoked, about $0.0005 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
polis-protocol
Set up and run a self-improving, multi-vendor AI agent team with the Polis Protocol — a markdown polis/ folder where each agent is a citizen with a capability card, tasks are contracts routed to whoever has the best track record by a learning router, settled work files lessons that compound into team memory, and…
media
Skill "media" from ymxlx/polis-protocol, covering polis protocol: a self-optimizing city of agents, the core idea, when this skill is active, structure of a polis and the first thing to do every session.
_data
Skill "_data" from ymxlx/polis-protocol, covering polis protocol: a self-optimizing city of agents, the core idea, when this skill is active, structure of a polis and the first thing to do every session.
subagent-driven-development
Execute plans via delegatetask subagents (2-stage review).
mcporter
List, auth, and call MCP servers/tools from the terminal.
research-engineer
An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.