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 mercurialsolo/claudectl --skill session-monitoringgit clone --depth 1 https://github.com/mercurialsolo/claudectlWrote 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/mercurialsolo/claudectl/session-monitoring)<a href="https://agentmods.dev/skills/mercurialsolo/claudectl/session-monitoring"><img src="https://agentmods.dev/badge/skills/mercurialsolo/claudectl/session-monitoring/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/mercurialsolo/claudectl/session-monitoring"><img src="https://agentmods.dev/badge/skills/mercurialsolo/claudectl/session-monitoring.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
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 →
- medium Excessive Agency · line 39 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00038 | $0.00631 |
| Opus 5 | $0.00019 | $0.00316 |
| Sonnet 5 | $0.00008 | $0.00126 |
| Haiku 4.5 | $0.00004 | $0.00063 |
Grade A, and why
Session Monitoring 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 13d 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 — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.
claudectl Session Monitoring
You have access to claudectl, a local session supervisor for Claude Code. Use it when the user asks about:
- How many sessions are running, their status, or what they're doing
- Session costs, burn rates, or budget tracking
- Session health (cognitive rot, loops, stalls, context saturation)
- Brain decisions, learning progress, or accuracy
- File conflicts between sessions
- Multi-session orchestration
Available CLI Flags
# Setup
claudectl --init # Wire up Claude Code hooks (one-time)
claudectl --init -s project # Wire up hooks for this project only
claudectl --uninstall # Remove claudectl hooks
# Session status
claudectl --list # Human-readable session list
claudectl --json # Machine-readable JSON with full data
claudectl --watch # Stream status changes
# Cost and history
claudectl --stats --since 24h # Aggregated statistics
claudectl --history --since 24h # Completed session history
claudectl --summary --since 8h # Activity summary
# Brain
claudectl --mode status # Show current brain gate mode
claudectl --mode on # Brain evaluates tool calls (default)
claudectl --mode off # Disable brain gate
claudectl --mode auto # Brain auto-approves above threshold
claudectl --brain-stats accuracy # Per-tool accuracy breakdown
claudectl --brain-stats learning-curve # Correction rate over time
claudectl --brain-stats baseline # Brain vs static rules comparison
claudectl --brain-stats false-approve # Safety: false positive rate
# Diagnostics
claudectl --doctor # Check terminal integration
claudectl --brain-prompts # List prompt template sources
Health Check Icons
When reporting session health from JSON output, these are the severity indicators:
- Critical: cognitive rot (score > 70), context > 90%, error loops
- Warning: context > 80%, cost spikes, stalls, early decay
- Info: proactive compaction suggestion, low cache
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.
- 13d ago First seen · 67 lines · 38 tokens per session scan A 865f19931331
Session Monitoring is a skill published in the GitHub repository mercurialsolo/claudectl (199 stars, last pushed 2mo ago), licensed MIT. It adds 38 tokens to every session and 631 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 2026-08-30.
Other skills, from other repositories
cw-dogfood
Use when a Codewhale change needs proving in the real product, or when asked to build/install/dogfood the local binaries: stamped release build, atomic install, fresh-shell verification, and the manual QA that gates cannot cover.
cw-gates
Use before claiming any Codewhale change is done, green, or ready to land: the focused-to-broad verification ladder, the budget checks CI enforces, and the rules for what counts as a passing test.
cw-land
Use when turning verified Codewhale work into commits, branches, or a merge: choosing direct-main vs. worktree vs. integration branch, preserving contributor credit, and honoring the gate artifact before merging.
cw-slice
Use before writing code for any Codewhale feature, upgrade, or refactor: find the existing owner of the behavior, bound the change to one reviewable slice, and fix the evidence bar before you start.
cw-handoff
Use when writing a Codewhale takeover prompt, continuation note, or end-of-session summary for another agent or a later session: a paste-ready handoff grounded in live state, with done/suspected/blocked kept separate.
cw-orient
Use at the start of any Codewhale work session, or when unsure which checkout, branch, or worktree is authoritative: establish live repo truth before reading a plan or editing a file.