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/ph3on1x/wisci/isolatenpx skills add ph3on1x/wisci --skill isolategit clone --depth 1 https://github.com/ph3on1x/wisciWrote 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/ph3on1x/wisci/isolate)<a href="https://agentmods.dev/skills/ph3on1x/wisci/isolate"><img src="https://agentmods.dev/badge/skills/ph3on1x/wisci/isolate.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 | $0.00061 | $0.00975 |
| Opus 5 | $0.00030 | $0.00487 |
| Sonnet 5 | $0.00012 | $0.00195 |
| Haiku 4.5 | $0.00006 | $0.00097 |
Grade A, and why
isolate scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/isolate — Subagent Research Delegator
Research happens in subagent context windows; only synthesized findings enter the main context. Durable findings are then persisted to the store so no future session repeats the work.
Store pre-flight
Existing store state:
!python3 "${CLAUDE_PLUGIN_ROOT}/scripts/wisci.py" scan
If the scan shows an error or unexpanded variable, run the bundled script manually: scripts/wisci.py relative to this skill's directory.
Before spawning anything, check the scan for a .wisci/context/ file covering the research topic:
- Fresh match: load it. Narrow the research to what it does not answer — or skip research entirely and present the stored knowledge.
- Stale match: research anyway; in the synthesis, reconcile against the stored file ("what changed since this was written").
- No match: research from scratch.
Execution Flow
-
Parse task. Read
$ARGUMENTS. Note override words:deep/thorough(wider sweep),save(force persist),nosave(inline only). -
Plan decomposition. Decide autonomously — no approval step. For each subtask pick the agent type:
- Codebase questions →
subagent_type: "Explore"(read-only) - External questions (library docs, best practices, comparisons) →
subagent_type: "general-purpose"with instructions to use web search/fetch - Hybrid tasks mix both.
Agent count: 1 for focused single-area research, 2-3 for natural splits, up to 5 only when
$ARGUMENTSsaysdeep/thorough. When multiple agents cover one topic, give each a distinct lens (code structure, git history, docs/web) rather than redundant copies of the same search. - Codebase questions →
-
Spawn all agents in a single message (parallel). Each prompt contains: the specific investigation task, focus areas, and the required output shape — structured markdown with exact file paths, line numbers, function names, and error messages. Vague summaries are not acceptable subagent output.
-
Collect and handle failures. An agent that returns nothing or dies: retry it once; still nothing → report the coverage gap explicitly in the synthesis. Never present partial coverage as complete.
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.
- 3d ago First seen · 70 lines · 61 tokens per session scan A 3e6b9ca298c2
isolate is a skill published in the GitHub repository ph3on1x/wisci (1 stars, last pushed 1mo ago), licensed MIT. It adds 61 tokens to every session and 975 once invoked, about $0.0003 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
contorium-workspace-memory
Use Contorium workspace memory layers (focus, session events, Git, export) when resuming AI work or avoiding repeated project explanation.
cli-logging-ux
Use this skill when editing or creating CLI output, logging, warnings, error messages, progress indicators, or diagnostic summaries in the APM codebase. Activate whenever code touches console helpers (richsuccess, richwarning, richerror, richinfo, richecho), DiagnosticCollector, STATUSSYMBOLS, CommandLogger, or any…
cut-release
Use this skill to cut an APM release from the current worktree: assess whether the cycle since the last tag warrants a patch or minor bump (semver discipline against the merged-since-last-tag diff), sanitize the [Unreleased] CHANGELOG block into a dated version block with one concise "so what" entry per merged PR…
docs-sync
Use this skill whenever a pull request is opened, reopened, or synchronized in microsoft/apm to assess whether and how the documentation corpus must change to stay truthful with the proposed code change. Activate even when the PR title or body says nothing about docs -- the skill must run on every PR to detect silent…
qmd
Search the vault using QMD semantic search. Use PROACTIVELY before reading files. Preference order: (1) MCP tools — mcpqmdquery, mcpqmdget, mcpqmdmultiget, mcpqmdstatus — if they appear in your tool menu, use them first; (2) CLI qmd --index ... as fallback; (3) Grep/Glob only when QMD is not installed. Trigger…
obsidian-cli
Interact with Obsidian vaults using the Obsidian CLI to read, create, search, and manage notes, tasks, properties, and more. Also supports plugin and theme development with commands to reload plugins, run JavaScript, capture errors, take screenshots, and inspect the DOM. Use when the user asks to interact with their…