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 Jarroslav/agentic-os --skill agentic-uninstallgit clone --depth 1 https://github.com/Jarroslav/agentic-osWrote 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/jarroslav/agentic-os/agentic-uninstall)<a href="https://agentmods.dev/skills/jarroslav/agentic-os/agentic-uninstall"><img src="https://agentmods.dev/badge/skills/jarroslav/agentic-os/agentic-uninstall.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 5.1 | $0.00203 | $0.04011 |
| Opus 5 | $0.00102 | $0.02005 |
| Sonnet 5 | $0.00041 | $0.00802 |
| Haiku 4.5 | $0.00020 | $0.00401 |
Grade A, and why
agentic-uninstall 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 6d 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 — 266 lines — stays where its author put it; the contents beside it link to each section on GitHub.
agentic-uninstall — role remover
You remove roles from a repo's scaffolded layer. This is not a deleter.
Deleting the files a preset lists would break the repo, because presets are
additive unions of shared template IDs — most of what qa lists is also
listed by developer.
The operation is a convergence: recompute what /agentic-init would have
produced for the presets that remain, then converge the repo to that state.
The governing invariant, which the acceptance harness asserts directly:
install(developer,qa)→uninstall(qa)==install(developer)
Everything below follows from it. If a step would leave the repo in a state a fresh install of the remaining roles could not produce, that step is wrong.
Conventions (PLUGIN, TARGET, journal shape, rendering rules incl. the
.json.tmpl quoted-array and newline-list conventions) are identical to
skills/agentic-init/SKILL.md — read its "Conventions" section first.
Like init and upgrade: never git add/git commit in the target repo.
Phase 0 — inputs and refusals
Read TARGET/.agentic/agentic-os/install.json. Missing ⇒ stop: "not installed
— nothing to remove." Then:
P_old = journal.answers.presets (legacy singular `preset` is read and normalised to a list)
P_new = P_old − removed (order preserved)
U_old = ∪ templates(P_old) G_old = ∪ generated(P_old)
U_new = ∪ templates(P_new) G_new = ∪ generated(P_new)
S_new = ∪ sdlc_skills(P_new) B_new = ∪ qe_blueprints(P_new)
Resolve unions from PLUGIN/presets/roles/*.json, the same way
agentic-upgrade re-resolves them.
Refuse and stop when:
- a named preset is not in
P_old— list what is installed, change nothing; journal.adoption.mode == "adopt-existing"— see Phase 6;P_newis empty and--allwas not passed — removing the last role is the whole-layer case and must be asked for explicitly.
Never re-run stack discovery. Reuse journal.stack_discovery verbatim,
inheriting init Phase 1's own rule. A fresh install on a repo whose stack has
since changed would render differently; that divergence is accepted and
declared, not chased.
What ships with it
2 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.
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.
- 6d ago First seen · 266 lines · 0 tokens per session scan A 922154e43aad
agentic-uninstall is a skill published in the GitHub repository Jarroslav/agentic-os (0 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 203 tokens to every session and 4,011 once invoked, about $0.0010 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 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…
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…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…