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 nomadop/session-watcher --skill sw-explaingit clone --depth 1 https://github.com/nomadop/session-watcherWrote 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/nomadop/session-watcher/sw-explain)<a href="https://agentmods.dev/skills/nomadop/session-watcher/sw-explain"><img src="https://agentmods.dev/badge/skills/nomadop/session-watcher/sw-explain/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/nomadop/session-watcher/sw-explain"><img src="https://agentmods.dev/badge/skills/nomadop/session-watcher/sw-explain.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00054 | $0.00644 |
| Opus 5.5 | $0.00022 | $0.00258 |
| Sonnet 5.5 | $0.00011 | $0.00129 |
| Haiku 4.5 | $0.00005 | $0.00064 |
Grade A, and why
sw-explain 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 18d 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 — 24 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Explain a Session Watcher metric
When the user asks about a metric:
- Call
watcher_status. Readbr,u(the arm it puts the session on), the lamp and the wallet clock'sphasefrom the reply'sreading; a falsereading.reliablemeans the session is still measuring, so say that instead of quoting values.mf,pp,wallandsweet / valleyare not inreading: point the user at where the host shows them, in Claude Code the dashboard at the URL the reply carries, in DSH the Session Watcher tab.mfis the hero chart's movable reading; the others are landmarks with no numeric readout. - Explain the requested metric in plain language.
- Contextualize against the flat-valley / AM-GM bound where relevant.
Metric glossary
- br (bill premium) — how far the bill sits above its cost at the sweet spot, as a fraction.
BR_AMBERandBR_REDare the zone boundaries.br = mf × pp. - mf (movable fraction) — the share of cost that timing can affect. AM-GM caps it at
√2−1, which is also why the reminder interval has a natural floor. Whatever sits above that share is cost no restart timing can reach. - pp — the timing-penalty shape term
(u−1)²/(2u); minimized at u=1 (the sweet spot). - u — normalized position, accumulated causally: each API call adds the fraction of a restart interval that the conditions in force for it imply, so u only moves forward and loading more files never walks it back. Short of a whole interval = left arm (cost still falling, so the lamp stays white or green); one whole interval = sweet; beyond it = past sweet. The lamp's colour is arm-gated this way; the carry-rent reminder is not, because it reads accumulated rent instead of the position.
uInst, the(x−1)/dhatratio, is reported beside the causaluas a diagnostic that nothing acts on. - wall — where continuing costs more per turn than a full restart.
- sweet / valley — the cost-curve minimum, reported as
xSweetand read off the reference skeleton fitted across the session's own path; the valley around it is flat (small timing penalty).
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.
- 18d ago Changed aaf5ba9a5bbd
- 21d ago Changed 8cdc676bf706
- 1mo ago Changed c1d763d4880c
- 1mo ago First seen · 24 lines · 54 tokens per session scan A 7feba52421aa
sw-explain is a skill published in the GitHub repository nomadop/session-watcher (5 stars, last pushed yesterday), licensed MIT. It adds 54 tokens to every session and 644 once invoked, about $0.0002 per session on Opus 5.5. 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
dvalin-security-scan
Scan code for injection, hardcoded secrets, XSS, dynamic code execution, and unsafe shell use. Use after writing or modifying code that handles user input, builds queries or commands, touches authentication, or adds a dependency — and whenever the user asks for a security check, audit, or review. Runs locally with no…
coding-agents-farm
To orchestrate parallel coding-agent farms (Claude, Codex, Copilot, Gemini, etc.) on isolated git worktrees.
coding-wrapped
Creates or refreshes a private local Coding Wrapped website from Claude Code and Codex session history. Use for Coding Wrapped, coding-agent fun facts, AI-coding behavior insights, a personal localhost coding dashboard, new insight cards, or an export of an existing Wrapped. Scans locally, excludes raw transcripts…
odds-api
Build custom apps, bots, dashboards, scanners, and MCP workflows using Odds API data access.
sol-governed-workers
Use when Codex work should route bounded implementation to lower-cost workers and reserve Sol for risky plan review or final evidence gates, or when installing or validating this workflow.
credit-optimizer
Automatically optimize AI agent credit usage by routing tasks to the most cost-efficient execution path. Use when you want to reduce AI API costs by 30-75% without quality loss, classify task complexity before execution, route simple tasks to free or low-cost models, split complex tasks into optimized sub-tasks, or…