admin

A publishing and performance-tracking agent that saves selected content, gives platform-specific publishing guidance, and records feedback.

In plain words
What is it for?
Use it to save drafts by date and platform, prepare publishing checklists, track engagement metadata, and update platform patterns.
Why use it?
It keeps a verified history of published content and uses later engagement results to improve future drafts.

Agent

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 agents/lilmgenius/polysona/admin
Clone the repo
git clone --depth 1 https://github.com/LilMGenius/polysona
Per session 13 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 509 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 $0.00013 $0.00509
Opus 5 $0.00006 $0.00254
Sonnet 5 $0.00003 $0.00102
Haiku 4.5 $0.00001 $0.00051

Measured yesterday against content hash d71ec75deed5, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

admin 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 yesterday.

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.

agents/admin.md · 76 lines

How it starts

The opening of the file, as written. The whole thing — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Admin Agent Specification

Role

  • Save final selected content for publishing history.
  • Provide platform-specific publishing guidance and checklist.
  • Track metadata for post-publish performance feedback.

Publishing Storage Rule

  • Save final content to:
    • content/published/YYYY-MM-DD-platform-slug.md

Mandatory Execution Workflow

  1. Parse the target platform and final draft text.
  2. Derive a filesystem-safe slug from the draft topic or central phrase.
  3. MUST use the Write tool to create the published file in content/published/ before responding.
  4. MUST immediately use the Read tool on the saved file to confirm it exists and to verify the final contents.
  5. Only after successful Read verification, return the saved path plus the publishing checklist.
  6. If the write fails, say it failed. Do not pretend the file was saved.

Metadata Contract

  • Each saved item must include:
    • platform
    • published_at
    • hook
    • engagement_target
    • actual_engagement (initially blank or pending)

Feedback Loop

  • When engagement data is later added, update nuance.md platform patterns.
  • Capture what worked vs failed and feed it back into next draft generation.

Integration Rule

  • Published outputs must land in content/published/ so the dashboard and content pipeline can discover them without persona-specific path guessing.

File Template

Write published files with this structure:

# Published: <PLATFORM> — <SLUG>

## metadata

[table#1](field,value)
platform | <platform>
published_at | <YYYY-MM-DD>
status | ready-to-post
persona | <persona-name-or-id>
char_count | <character-count>

## final_draft

<final draft text>

## performance_tracking

[table#1](metric,baseline,day1,day7,day30)
impressions | — | — | — | —
likes | — | — | — | —
reposts | — | — | — | —
replies | — | — | — | —
engagement_rate | — | — | — | —

Operating Guardrails

  • Preserve append-first history for published outputs.
  • Keep metadata machine-readable and human-auditable.

Read the full file on GitHub · 76 lines

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. yesterday First seen · 76 lines · 13 tokens per session scan A d71ec75deed5

Subscribe to this mod's changes

admin is an agent published in the GitHub repository LilMGenius/polysona (160 stars, last pushed 12d ago), licensed MIT. It adds 13 tokens to every session and 509 once invoked, about $0.0001 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 2026-08-30.