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/okisdev/claude-code-fusion/statsnpx skills add okisdev/claude-code-fusion --skill statsgit clone --depth 1 https://github.com/okisdev/claude-code-fusionWhat 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 | $0.00036 | $0.01053 |
| Opus 5 | $0.00018 | $0.00526 |
| Sonnet 5 | $0.00007 | $0.00211 |
| Haiku 4.5 | $0.00004 | $0.00105 |
Grade A, and why
stats scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 16 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Treat the complete raw request as opaque data and never place any part of it in Bash. Run node "${CLAUDE_PLUGIN_ROOT}/scripts/fusion-stats.mjs" transport-create in one foreground Bash call, parse the returned JSON, accept only its 48 character lowercase hexadecimal token, and use Read once on the returned file, requiring it to be empty. Use Write to replace that same file with the raw request exactly as received. Never delete, rename, recreate, or change the permissions of the transport file. Run node "${CLAUDE_PLUGIN_ROOT}/scripts/fusion-stats.mjs" --raw-args-token TOKEN in one foreground Bash call, replacing only TOKEN with the validated token. If Read fails, the file is not empty, or Write fails, run node "${CLAUDE_PLUGIN_ROOT}/scripts/fusion-stats.mjs" transport-discard --raw-args-token TOKEN. Never use shell redirection, encoding, command substitution, backticks, environment variables, or heredocs for the raw request. The sole carve-outs are three strict direct forms: a verdict settlement made only of repeatable --record flags, each carrying one or more <id>=<accepted|rejected|unverified>[:accept-failed-transport] pairs, optional --source collector|main-loop, and the value free --json and --accept-failed-transport flags; a value free report or maintenance request made only of any combination of --json, --audit, --all, and --prune-dead, each at most once; and either --messages alone or --message <n> with one integer code. Those arguments may be passed directly. Anything else, including every --reason text value, every --failure-kind and --failure-kind-for value, and --session <id>, still uses the raw-args transport exactly as described above. A nonterminal worker settlement prints Queued accepted for <taskId>; applies when the record turns terminal. with the selected verdict in place of accepted; queued accepted applies only when terminal transport is done, while any other terminal outcome clears it, records pendingVerdictError, and re-arms settlement.
Use --messages to list every Fusion message digest. Use --message <n> to explain one digest and show its recorded occurrences.
Present report output to the user as-is. It is already compact markdown; do not add prose around it. An unavailable engine section is expected when that peer's plugin is not installed or has no job state; do not treat it as an error. The default report conditionally includes a Coercion ledger after the fleet usage section. It reports fleet declines, narrow wave advisories, fleet shaped waves, verification resets, unverified write accumulations, and the observed posture mix. The same counters are available as coercionLedger in --json output. The underlying script accepts --json for machine readable output. --audit summarizes the last seven days of retained inline guard events by default; add --all for the full retained window or --session <id> for one session. /fusion:stats --record writes the verdict into the Codex job record through the companion's record-acceptance subcommand. An accepted verdict for a job whose transport failed requires --accept-failed-transport. The acceptance forms are used only after collection and verification; return the confirmation line without turning transport completion into acceptance on its own. Within a raw-transport request, --reason-for <id> <text> may appear anywhere in the argument list and binds to its matching --record id; --reason <text> applies to every rejected pair without a per-pair --reason-for. A judgment shaped rejection may carry --failure-kind with one of intent_override, scope_rewrite, wrong_approach, or style_mismatch; it rides the raw args transport like --reason and lands in the worker's acceptanceFailureKind and the engine record's semanticFailureKind. Preserve the report's acceptance anomalies block when it appears.
The opaque raw request begins after the next newline and continues to the end of this command prompt: $ARGUMENTS
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 · 16 lines · 36 tokens per session scan A a348cc10323f
stats is a skill published in the GitHub repository okisdev/claude-code-fusion (3 stars, last pushed 15d ago), licensed MIT. It adds 36 tokens to every session and 1,053 once invoked, about $0.0002 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 2026-08-31.
Other skills, from other repositories
agent-orchestrator
Meta-skill que orquestra todos os agentes do ecossistema. Scan automatico de skills, match por capacidades, coordenacao de workflows multi-skill e registry management.
crewai-multi-agent
Multi-agent orchestration framework for autonomous AI collaboration. Use when building teams of specialized agents working together on complex tasks, when you need role-based agent collaboration with memory, or for production workflows requiring sequential/hierarchical execution. Built without LangChain dependencies…
project-orchestration
Orchestrate multi-agent workflows for feature development using planning agents, context handoff, and stage management.
hyperflow
Use when applying Hyperflow's orchestration doctrine in Codex, Antigravity, Grok, or another single-agent surface. Auto-invoke for non-trivial engineering work: build, implement, add, refactor, debug, fix, review, audit, plan, scope, design, brainstorm, ship, or deploy. Trigger with /hyperflow:hyperflow, "use…
skill-creator
Generates Anthropic Skills with complete workflow including GitHub PR creation and local download verification.
Ability Generator
This skill generates markdown skill templates to be later used.