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 jeremylongworth-source/AgentSkills --skill skill-token-overhead-reviewgit clone --depth 1 https://github.com/jeremylongworth-source/AgentSkillsWrote 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/jeremylongworth-source/agentskills/skill-token-overhead-review)<a href="https://agentmods.dev/skills/jeremylongworth-source/agentskills/skill-token-overhead-review"><img src="https://agentmods.dev/badge/skills/jeremylongworth-source/agentskills/skill-token-overhead-review/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/jeremylongworth-source/agentskills/skill-token-overhead-review"><img src="https://agentmods.dev/badge/skills/jeremylongworth-source/agentskills/skill-token-overhead-review.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 | $0.00052 | $0.00543 |
| Opus 5 | $0.00026 | $0.00271 |
| Sonnet 5 | $0.00010 | $0.00109 |
| Haiku 4.5 | $0.00005 | $0.00054 |
Grade A, and why
skill-token-overhead-review 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 7d 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 — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill Token Overhead Review
Core Workflow
- Identify the skill or bundle, trigger path, host, loaded files, tools/scripts used, repeated-run pattern, and target artifact.
- Estimate overhead from added metadata, instructions, references, tool calls, turns, command output, MCP tools, or setup steps. Use exact token counts only when measured.
- Compare overhead against output improvement from scenario or before/after evidence.
- Flag broad triggers, duplicate guidance, stale references, unnecessary scripts, oversized command output, and host-specific setup leakage.
- Recommend keep, trim, split, merge, lazy-load, compose through a skillset or orchestrator, move to references/scripts, isolate in a host adapter, or defer.
- Preserve essential safety and validation instructions even when trimming.
Measurement Protocol
- Capture baseline and skill-enabled runs with the same prompt and source material when practical.
- Record activated skills, referenced files, scripts/commands, MCP servers or tools, output size, turns, and validation results.
- For repeated workflows, check whether raw research, tool output, or reasoning compounds across items or runs.
- Treat host-specific features separately. For example, Claude Code
context: fork,!command, and MCP Tool Search can reduce main-context load, but they are adapter behaviors rather than portable skill requirements. - Do not count shell injection as free context: inserted command output still becomes prompt content.
Safety Rules
- Do not remove safety, approval, freshness, or validation guidance only to save context.
- Do not optimize for token count when the task is high-risk and needs review boundaries.
- Do not claim exact token savings unless measured.
- Do not add host-specific optimization fields to portable skills without a compatibility note or adapter boundary.
Deliverable Shape
For overhead reviews, provide:
- Skill or bundle reviewed
- Loaded context and tools
- Overhead estimate
- Measurement method and limits
- Output value observed
- Duplicative or stale guidance
- Trim/split/merge/compose recommendations
- Host adapter recommendations
- Safety instructions to preserve
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.
- 7d ago First seen · 66 lines · 52 tokens per session scan A 6a34eafca9e2
skill-token-overhead-review is a skill published in the GitHub repository jeremylongworth-source/AgentSkills (1 stars, last pushed 9d ago), licensed MIT. It adds 52 tokens to every session and 543 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 2026-09-03.
Other skills, from other repositories
issue-authoring
Draft or refine IDD-ready GitHub issues, roadmap issues, and sub-issues before the normal IDD execution loop begins. Use when a request is too large or ambiguous for one reviewable change, when work needs decomposition or dependency encoding, or when the user asks for issue drafting, roadmap planning, or…
idd-spec-audit
Semantic audit of the IDD instruction corpus for leaked session context, cross-file contradictions, fresh-memory completability gaps, automation blockers, and restatement-discipline drift. Use on request to audit .github/instructions, the issue-authoring skill bundle, and the installed agent entry files (CLAUDE.md…
unity-yaml-format
Inspect, explain, diff, and carefully edit Unity text-serialized files such as .unity, .prefab, .asset, and related YAML-based project files. Use when mapping class IDs and fileIDs, tracing object references, reviewing merge conflicts, or making minimal safe edits to existing UnityYAML documents.
joedevflow
Development workflow. Use when building a feature, creating an MVP, refactoring code, fixing a bug, or any task that involves writing or changing implementation code.
authos-web-integration
Integrate AuthOS into browser, React, Vue, or plain TypeScript applications using @drmhse/sso-sdk and the AuthOS React/Vue adapters. Use when adding OAuth redirects, password login, magic links, passkeys, MFA callback handling, token refresh, or frontend session state.
authos-backend-integration
Secure backend APIs with AuthOS-issued JWTs and the AuthOS Node server adapter. Use when building an API that must verify AuthOS bearer tokens, enforce JWT claims, add Express middleware, validate JWKS keys, or create a backend-owned session after a browser OAuth callback.