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 OutlineDriven/odin-claude-plugin --skill setup-pstackgit clone --depth 1 https://github.com/OutlineDriven/odin-claude-pluginWrote 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/outlinedriven/odin-claude-plugin/setup-pstack)<a href="https://agentmods.dev/skills/outlinedriven/odin-claude-plugin/setup-pstack"><img src="https://agentmods.dev/badge/skills/outlinedriven/odin-claude-plugin/setup-pstack/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/outlinedriven/odin-claude-plugin/setup-pstack"><img src="https://agentmods.dev/badge/skills/outlinedriven/odin-claude-plugin/setup-pstack.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high System Prompt Leakage · line 43 Skill contains instructions that could directly expose system prompts, internal rules, or hidden instructions to users or external parties.Fix: Remove any instructions that reveal, print, or output system prompts or internal rules. System instructions should never be exposed to end users.
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 | $0.00048 | $0.00786 |
| Opus 5.5 | $0.00019 | $0.00314 |
| Sonnet 5.5 | $0.00010 | $0.00157 |
| Haiku 4.5 | $0.00005 | $0.00079 |
Grade A, and why
setup-pstack 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 1mo 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 — 46 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Setup pstack
Contract
| Field | Bound contract |
|---|---|
| Trigger | Configure pstack role-to-model choices. |
| Authority | Write only to the named local pstack rule file; rollback path is removal or revert. |
| Side effect | Writes one user-level pstack model rule file. |
| Done | Every pstack role maps to a model in the available-models set. |
Inputs
- Role–model mappings (required): one or more
role: modelpairs to write. Each role name must be non-empty. Each model name must be non-empty. - Rule file path (required): absolute path to the user-level pstack rule file.
- Available models (required): the set of model names the user's pstack installation can resolve, supplied by the user (for example, the output of the user's model-listing command). Used to validate that every supplied model is resolvable before writing.
- Existing rule file content (optional): current file contents if it already exists, used to detect drift.
Procedure
- Validate inputs. Stop if any role name is empty, any model name is empty, or the rule file path is not an absolute path. Verify each supplied model is in the available-models set; stop with
unavailable-modelif any model is not in the set. Done when: every role and model is non-empty, every model is in the available-models set, and the path is absolute. - Read existing file if it exists. Record its content for the rollback record. When existing rule file content was supplied, compare it against the actual file content and report any drift (supplied content that no longer matches the file) before proceeding. Done when: the original content is recorded or confirmed absent, and any drift is reported.
- Parse existing rules to produce a map of role → model. Done when: the map is built or a malformed line is reported.
- Merge: for each supplied role–model pair, set or overwrite the entry in the map. Done when: every supplied pair is in the map.
- Serialize: write the map as
role: modellines, sorted by role. Done when: the file is written with all roles sorted. - Confirm done: re-read the written file and verify every supplied role maps to its model and that every model is in the available-models set. Done when: every supplied role resolves to a model in the available-models set in the file.
- Return the final file path, a rollback record (original content or
(no prior file)), and a human-readable summary. Done when: the summary is emitted.
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.
- 1mo ago First seen · 46 lines · 48 tokens per session scan A 4c7dfa8766e1
setup-pstack is a skill published in the GitHub repository OutlineDriven/odin-claude-plugin (39 stars, last pushed 27d ago), licensed Apache-2.0. It adds 48 tokens to every session and 786 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 2026-09-04.
Other skills, from other repositories
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-optimizer
Optimize the meaningful UI available immediately from a Next.js route on an initial load (hard navigation) or named client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route and entry point at a time; the shipped test then guards…