agentmods.dev

unpublish

A document-removal tool for published AI-docs files, deleting the matching Markdown and HTML pair from the configured GitHub Pages repository. GitHub Pages is GitHub's service for hosting web pages from a repository.

In plain words
What is it for?
Use it to unpublish, retract, or remove a named published document from the configured repository.
Why use it?
It provides a controlled way to take a published document offline while requiring confirmation before deletion and keeping the files in Git history.

Skill for Claude CodeCodex

6 3mo ago A scan 109 tokens original MIT
View the source file quantumentangled-dev/ai-docs-plugin
Install

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.

agentmods
npx agentmods add skills/quantumentangled-dev/ai-docs-plugin/unpublish
Any agent
npx skills add quantumentangled-dev/ai-docs-plugin --skill unpublish
Clone the repo
git clone --depth 1 https://github.com/quantumentangled-dev/ai-docs-plugin

Made for: Claude Code, Codex.

Per session 109 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,504 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00109 $0.01504
Opus 5 $0.00055 $0.00752
Sonnet 5 $0.00022 $0.00301
Haiku 4.5 $0.00011 $0.00150

Measured 2d ago against content hash 5514d4668815, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

unpublish 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 2d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/delete.sh), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

skills/unpublish/SKILL.md · 114 lines

How it starts

The opening of the file, as written. The whole thing — 114 lines — stays where its author put it; the contents beside it link to each section on GitHub.

unpublish

Drop a previously published .md + .html pair from the configured GitHub Pages repo. URL 404s after next Pages build (1–3 min); git history preserves the file.

When to fire

Should trigger:

  • "unpublish q2"
  • "delete the published deck"
  • "remove postmortem from ai-docs"
  • "take down the q2 report"
  • "retract the deck"
  • "/ai-docs:unpublish q2"

Should NOT trigger:

  • "delete this file" (CWD-local, no slug context) → ambiguous; ask before assuming
  • "publish q2" / "republish q2" → publish skill
  • "summarize this URL" → read skill

Repo boundary

Deletes ONLY from the configured repo (user-scope ~/.config/ai-docs/config.json OR project-scope <proj>/.ai-docs/config.json via walk-up marker). Refuse non-configured repos.

Cardinal Rule

ALWAYS fire AskUserQuestion confirm before delete.sh. No "Yes" at Phase B → no commit.

Orchestration (main thread)

Phase A — discovery + propose

  1. REPO=$(${CLAUDE_PLUGIN_ROOT}/skills/publish/scripts/_config.sh read | jq -r '.repo'). Empty or nonzero → "Run /ai-docs:publish once to set up your repo, then re-try unpublish.", STOP.
  2. For each named slug: ${CLAUDE_PLUGIN_ROOT}/skills/publish/scripts/find-remote.sh --repo "$REPO" --slug "<slug>". Multi-slug: parallel Bash tool calls in one turn.
  3. Classify each slug's path<TAB>sha lines:
    • 0 hits → not-published; surface "no published doc matching <slug>" and skip. NEVER infer an alternative slug, NEVER reinterpret the request as a creation/edit task.
    • 1–2 hits, all basenames exactly <slug>.md and/or <slug>.html in a single dir → clear; record paths.
    • Anything else (3+ hits, multi-dir hits, OR basenames don't exactly match <slug>.{md,html} e.g. <slug>-foo.md returned) → ambiguous; group by dirname into path-pair candidates and require AskUserQuestion at step 4. NEVER silently proceed.
  4. For each ambiguous slug, fire AskUserQuestion: "<slug> has N published locations. Which to delete?" — options (≥2): one per candidate path-pair (label = dirname), plus Both (if 2 candidates) or All (if 3+). Record selection.
  5. Emit Phase A summary:

Read the full file on GitHub · 114 lines

Files

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.

Changes

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.

  1. 2d ago First seen · 114 lines · 109 tokens per session scan A 5514d4668815

Subscribe to this mod's changes

unpublish is a skill published in the GitHub repository quantumentangled-dev/ai-docs-plugin (6 stars, last pushed 3mo ago), licensed MIT. It adds 109 tokens to every session and 1,504 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 2026-08-31.

Backend and APIsDocumentsWriting and docs
Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

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.

microsoft/vscode · 53 tokens

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…

microsoft/vscode · 71 tokens

agent-host-chat-contributions

Build and review cross-cutting agent-host chat behavior through lifecycle contributions. Use when adding turn lifecycle side effects, prompt or context injection, restored-history transformation, protocol-action observation, or when reviewing changes that add code to AgentSideEffects or AgentService.

microsoft/vscode · 56 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens