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 cost-reportgit 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/cost-report)<a href="https://agentmods.dev/skills/jmagly/aiwg/cost-report"><img src="https://agentmods.dev/badge/skills/jmagly/aiwg/cost-report/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/cost-report"><img src="https://agentmods.dev/badge/skills/jmagly/aiwg/cost-report.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Excessive Agency · line 81 Skill selects an external model or provider that may use a different account or billing plan than the operator expects. Undisclosed model switches can cause unexpected cost or quota consumption.Fix: Remove the model/provider override or disclose it prominently and require explicit operator approval before invoking an external coding CLI or billed model.
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 | $0.00021 | $0.01526 |
| Opus 5 | $0.00010 | $0.00763 |
| Sonnet 5 | $0.00004 | $0.00305 |
| Haiku 4.5 | $0.00002 | $0.00153 |
Grade A, and why
cost-report 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 — 195 lines — stays where its author put it; the contents beside it link to each section on GitHub.
cost-report
You generate a cost and token-spending report for the current or most recent workflow session. You read accumulated token usage data from .aiwg/ralph/cost-tracking.json and present a breakdown by operation, model, and time period.
Triggers
Alternate expressions and non-obvious activations (primary phrases are matched automatically from the skill description):
- "how much did that cost" → report for most recent session
- "what did this iteration cost" → report scoped to current agent loop
- "token breakdown" → report with per-model detail
- "did we stay in budget" → report with budget threshold comparison
Trigger Patterns Reference
| Pattern | Example | Action |
|---|---|---|
| Session cost | "cost report" | aiwg cost-report |
| Current loop cost | "how much has this session cost so far" | aiwg cost-report --session current |
| Named session | "cost for the greenfield run" | aiwg cost-report --session greenfield |
| Model breakdown | "show costs by model" | aiwg cost-report --by-model |
| Budget check | "are we over budget" | aiwg cost-report --budget <N> |
| Fleet spend | "show fleet spend" | aiwg cost-report --fleet |
Behavior
When triggered:
Fleet mode
For --fleet, run the native CLI handler. It reads ~/.config/aiwg/fleet.yaml, resolves each key_ref only from ~/.config/aiwg/keys/ or AIWG_OPENROUTER_KEY_*, and reports bot | machine | spend MTD | cap | % used | top-3 expensive sessions.
Fleet manifests contain references only. Never read a credential from a project manifest, print a credential, or copy one into an artifact. AIWG observes and correlates spend; OpenRouter enforces all limits and caps. Session/model correlation is optional and uses locally recorded bot=, session=, and generation_id= tags in .aiwg/activity.log.
aiwg cost-report --fleet
aiwg cost-report --fleet --json
aiwg cost-report --key <key_ref> --monthly-cap 10
For setup and security details, see @$AIWG_ROOT/docs/guides/openrouter-fleet-costs.md.
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 · 195 lines · 21 tokens per session scan A 7af06563c914
cost-report is a skill published in the GitHub repository jmagly/aiwg (211 stars, last pushed yesterday), licensed MIT. It adds 21 tokens to every session and 1,526 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.