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 agentmods add skills/samibs/skillfoundry/costnpx skills add samibs/skillfoundry --skill costgit clone --depth 1 https://github.com/samibs/skillfoundryWhat 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 | $0.00010 | $0.02967 |
| Opus 5 | $0.00005 | $0.01484 |
| Sonnet 5 | $0.00002 | $0.00593 |
| Haiku 4.5 | $0.00001 | $0.00297 |
Grade A, and why
cost 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 2d 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 — 336 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/cost - Token Usage and Cost Analyst
You are the Cost Analyst. You collect token usage data, compute costs against model pricing, and generate actionable reports with budget alerts and optimization recommendations. You help developers understand and control their AI spending.
Persona: See agents/_cost-routing.md for cost routing protocol.
Reflection Protocol: See agents/_reflection-protocol.md for reflection requirements.
OPERATING MODE
/cost Full cost report (all breakdowns)
/cost summary Quick totals only
/cost --by=agent Group by agent type
/cost --by=story Group by story
/cost --by=phase Group by execution phase
/cost --by=model Group by model used
/cost session Current session costs only
/cost trend Show cost trends over last 5 sessions
/cost budget [amount] Set budget threshold (warn at 80%, block at 100%)
/cost reset Clear cost data (requires confirmation)
PHASE 1: COLLECT USAGE DATA
1.1 Data Sources
Gather token usage from all available sources:
DATA SOURCES:
1. .claude/metrics.json -- /go execution metrics
2. .claude/state.json -- Current execution state
3. memory_bank/knowledge/agent-stats.jsonl -- Agent performance data
4. logs/remediations.md -- Auto-fix token overhead
5. scripts/cost-tracker.sh -- Shell-based cost tracking
1.2 Collect Current Session Data
# Attempt to read existing cost data
if [ -f "./scripts/cost-tracker.sh" ]; then
./scripts/cost-tracker.sh report --by=all
fi
# Read metrics file
if [ -f "./.claude/metrics.json" ]; then
# Parse agent invocations, token counts, durations
fi
1.3 Handle Missing Data
IF no cost data exists:
OUTPUT:
NO COST DATA AVAILABLE
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
No token usage has been recorded yet.
Cost tracking is automatic during:
- /go execution (all modes)
- /gosm, /goma, /blitz runs
- Individual agent invocations
Run a /go execution to start collecting data.
EXIT.
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.
- 2d ago First seen · 336 lines · 10 tokens per session scan A f35e4e38b88d
cost is a skill published in the GitHub repository samibs/skillfoundry (12 stars, last pushed 1mo ago), licensed MIT. It adds 10 tokens to every session and 2,967 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.
Other skills, from other repositories
memorix-sessions
Use when resuming work, preparing handoff context, binding an HTTP control-plane project, or deciding whether sessionstart is useful.
memorix-troubleshooting
Use when Memorix MCP, setup, project binding, HTTP control plane, hooks, skills, or agent integration is missing, stale, or failing.
ring:applying-composition-patterns
React composition patterns that scale. Avoid boolean prop proliferation by using compound components, lifting state, and composing internals. Use when refactoring components with boolean prop proliferation, building flexible component libraries, or during architecture review. Skip for simple components with 1-2 props…
ring:searching-code
Forensic code search and analysis with optional Chain of Draft (CoD) ultra-concise mode. Five-phase methodology (clarification, planning, execution, analysis, synthesis) with severity assessment. Use for targeted investigation of specific patterns, bugs, or vulnerabilities. Skip for broad architecture mapping (use…
ring:exploring-codebases
Exploring a codebase across phases: scopes the target, detects architecture, components, and layers, deep-dives each discovered perspective, then synthesizes findings into actionable guidance with file:line evidence. Use to understand how a feature or system works before planning changes, or to orient on an unfamiliar…
ring:auditing-dependency-security
Auditing a dependency for supply-chain risk before install (pip/npm/go/cargo): checks typosquatting, maintainer/age risk, vulnerability DBs (OSV, GHSA, Socket), and lockfile hash pinning, then emits a risk score and approve/conditional/escalate/block decision. Use when adding or updating a dependency, reviewing a…