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 jmagly/aiwg --skill metrics-tokensgit clone --depth 1 https://github.com/jmagly/aiwgWrote 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/jmagly/aiwg/metrics-tokens)<a href="https://agentmods.dev/skills/jmagly/aiwg/metrics-tokens"><img src="https://agentmods.dev/badge/skills/jmagly/aiwg/metrics-tokens/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/jmagly/aiwg/metrics-tokens"><img src="https://agentmods.dev/badge/skills/jmagly/aiwg/metrics-tokens.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00019 | $0.01636 |
| Opus 5 | $0.00010 | $0.00818 |
| Sonnet 5 | $0.00004 | $0.00327 |
| Haiku 4.5 | $0.00002 | $0.00164 |
Grade A, and why
metrics-tokens 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 — 218 lines — stays where its author put it; the contents beside it link to each section on GitHub.
metrics-tokens
You perform deep analysis of token usage efficiency. You compare AIWG workflow token consumption against the MetaGPT 124 tokens/line benchmark (REF-013), identify high-cost operations, and surface optimization opportunities.
Triggers
Alternate expressions and non-obvious activations (primary phrases are matched automatically from the skill description):
- "how efficient are my tokens" → efficiency ratio vs MetaGPT baseline
- "am I above the baseline" → threshold status check
- "where are tokens being wasted" → per-step breakdown with recommendations
- "token ratio" → tokens/line ratio calculation
Trigger Patterns Reference
| Pattern | Example | Action |
|---|---|---|
| Efficiency report | "token efficiency" | aiwg metrics-tokens |
| Session analysis | "analyze tokens for this session" | aiwg metrics-tokens --session current |
| Threshold check | "are we at green" | aiwg metrics-tokens --threshold |
| Per-step breakdown | "which step used the most tokens" | aiwg metrics-tokens --by-step |
| Optimization hints | "suggest token optimizations" | aiwg metrics-tokens --optimize |
Behavior
When triggered:
-
Determine scope:
- Default: current or most recent session
--session <name>: named session--all: aggregate across all sessions
-
Load token data:
- Read
.aiwg/ralph/sessions/*/metrics.jsonfor raw token counts - Apply estimation heuristic: 4 chars per token (aligned with
src/metrics/token-counter.ts)
- Read
-
Compute efficiency metrics:
- Tokens/line ratio for session output
vsBenchmark: percentage vs MetaGPT 124 tokens/line (negative = better)vsBaseline: percentage vs typical LLM 200 tokens/line (negative = better)- Threshold status: green (≤124), yellow (125–150), red (>150)
-
Run the command:
# Default efficiency report aiwg metrics-tokens # Current session aiwg metrics-tokens --session current # Per-step breakdown aiwg metrics-tokens --by-step # With optimization suggestions aiwg metrics-tokens --optimize # JSON output aiwg metrics-tokens --json
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 · 218 lines · 19 tokens per session scan A 393403c9a8a9
metrics-tokens is a skill published in the GitHub repository jmagly/aiwg (211 stars, last pushed 2d ago), licensed MIT. It adds 19 tokens to every session and 1,636 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 2026-09-03.
Other skills, from other repositories
surge
Use when a user provides a PRD, spec, or detailed requirements document and needs a full project delivered through iterative expert orchestration — multi-round analyze/research/design/implement/QA cycles with convergence detection. NOT for: single-file edits, quick prototypes, simple Q&A, or tasks without a written…
goal-writer
Drafts a goal+rider document pair that briefs an autonomous coding agent on one round of work — a goal file under 4,000 characters (sized to fit the /goal command in both Claude Code and Codex) plus an unbounded rider with phased plans and named depth tests. Use when the user says "draft a goal", "write a goal+rider"…
horizon
Run a durable Horizon workflow for a multi-feature goal with bounded autonomous retries and an audit trail.
check-in
Record a Parallax protocol checkpoint with concrete evidence before gated implementation work.
debug
Perform an evidence-based Parallax diagnosis or post-build audit and verify the repair.
hyperplan
Harden a non-trivial plan through a three-round adversarial critique and evidence-based synthesis.