Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add nagisanzenin/idiolect/plugin install idiolectWrote 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/nagisanzenin/idiolect/campaign)<a href="https://agentmods.dev/skills/nagisanzenin/idiolect/campaign"><img src="https://agentmods.dev/badge/skills/nagisanzenin/idiolect/campaign/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/nagisanzenin/idiolect/campaign"><img src="https://agentmods.dev/badge/skills/nagisanzenin/idiolect/campaign.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00046 | $0.01061 |
| Opus 5 | $0.00023 | $0.00531 |
| Sonnet 5 | $0.00009 | $0.00212 |
| Haiku 4.5 | $0.00005 | $0.00106 |
Grade A, and why
campaign scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 48 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/idiolect:campaign — many voices, zero bleed
The failure mode of one writer producing N "different" posts is convergence: same skeleton, same rhythm, swapped adjectives. This skill prevents it structurally — each post is written in an isolated context that has seen ONLY its own voice, then the set is checked for overlap like the adversarial reviewer a real editor would be.
Setup
ROOT="${CLAUDE_PLUGIN_ROOT:-${CODEX_PLUGIN_ROOT:-$IDIOLECT_ROOT}}"
# unset everywhere (opencode)? ROOT = two directories up from this SKILL.md
IDIO="python3 $ROOT/scripts/idiolect.py"
CID="<campaign-name-or-date-slug>"
Flow
-
Cast the voices. Brief to a scratch file, then
$IDIO pick --platform <p> --brief-file <f> --n <N> --distinct --json(per-platform picks if the campaign spans platforms — and pass--excludewith every already-cast slug on each subsequent pick, or the same voice will happily win two platforms).--distinctdoes greedy max-distance casting — announce the cast in one line each: who, platform, why they fit the brief. If the user named people fuzzily ("use the nurse and the sneaker guy"), resolve those against$IDIO voices --jsonfirst and fill the rest of the cast withpick. Nothing here requires the user to know a slug or a flag. -
Pre-assign structure. Build a rotation table before any writing: no two posts share (opener, shape) even across different voices; lengths vary. This is the campaign-level variance guard; the per-voice ledger check comes free in step 3.
-
Fan out, isolated. For each (voice, platform, structure) row, spawn an
idiolect-writeragent whose prompt contains ONLY: the voice profile path, the brief, the platform, the assigned structure, and the two shared docs' paths. One writer never sees another writer's voice or output — isolation is what prevents bleed; parallelism is just the bonus. Each writer self-verifies withscan+conformand saves to<scratch>/post-<slug>.txt. Codex/opencode fallback (no auto-spawn): write them yourself SEQUENTIALLY, and before each post re-read that voice's profile in full and consciously drop the previous voice's rhythm; the verification gates below still catch bleed if you fail.
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.
- 9d ago First seen · 48 lines · 46 tokens per session scan A fdef5308362d
campaign is a skill published in the GitHub repository nagisanzenin/idiolect (23 stars, last pushed 2mo ago), licensed MIT. It adds 46 tokens to every session and 1,061 once invoked, about $0.0002 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 2026-09-01.
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…
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…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…