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 ussumant/useful-agent-skills --skill fable-low-powergit clone --depth 1 https://github.com/ussumant/useful-agent-skillsWrote 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/ussumant/useful-agent-skills/fable-low-power)<a href="https://agentmods.dev/skills/ussumant/useful-agent-skills/fable-low-power"><img src="https://agentmods.dev/badge/skills/ussumant/useful-agent-skills/fable-low-power/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/ussumant/useful-agent-skills/fable-low-power"><img src="https://agentmods.dev/badge/skills/ussumant/useful-agent-skills/fable-low-power.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 | $0.00108 | $0.01287 |
| Opus 5 | $0.00054 | $0.00643 |
| Sonnet 5 | $0.00022 | $0.00257 |
| Haiku 4.5 | $0.00011 | $0.00129 |
Grade A, and why
fable-low-power 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 11d 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 — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Fable Low Power Mode
A power profile, not a new orchestrator. This skill defines what CHANGES when your Anthropic usage limits run low, and how the mode switches.
State machine
State file: ~/.claude/fable-low-power.json ·
Sensor: ~/.claude/skills/fable-low-power/limit-sense.sh
- Signal:
rate_limits.five_hour/.seven_day.used_percentagefrom the statusline payload Claude Code pipes per render tick, teed to~/.claude/cache/statusline-payload.jsonbystatusline-tee.sh. No credentials involved. If you replace the statusline script, keep the tee. - Modes:
auto(default — thresholds decide) ·on/off(manual, outranks auto). - Auto thresholds (in the state file): ON when 5h ≥ 60% or 7d ≥ 75%; back OFF only when 5h < 40% and 7d < 65% (hysteresis, no flapping). Reading stale >30 min → hold last state.
- Trigger:
low-power-mode.shannounces ON at session start and mid-session flips at prompt boundaries. Announcements instruct the session to invoke this skill.
Subcommands (when invoked as /fable-low-power …)
| Args | Do |
|---|---|
(none) / status |
bash ~/.claude/skills/fable-low-power/limit-sense.sh → report effective state, mode, 5h/7d %, resets, thresholds, and frontier burn (fable_today / fable_7d / workers_today) — one screen. |
on |
bash ~/.claude/skills/fable-low-power/limit-sense.sh set-mode on → confirm, then APPLY the profile below immediately in this session. |
off |
bash ~/.claude/skills/fable-low-power/limit-sense.sh set-mode off → confirm normal routing resumed. |
auto |
bash ~/.claude/skills/fable-low-power/limit-sense.sh set-mode auto → report what auto currently decides. |
Usage tracking
The statusline tee also writes a per-session ledger:
~/.claude/cache/usage-sessions/<session_id>.json — cumulative model, cost,
and main-loop token totals, atomically overwritten per tick (last write =
session totals). limit-sense.sh aggregates it into:
fable_today— sessions whose main loop matchesmodel_match(default"fable", editable in the state file), active today: count, cost_usd, in/out tokens.out_tokensis the main loop only, so it's the closest proxy for "what the frontier model itself generated";cost_usdincludes in-session subagents.fable_7d— same over the trailing 7 days (matches the weekly limit window).workers_today— interactive sessions on other models. Headless-pruns never tick a statusline, so they don't appear.
What ships with it
4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 11d ago First seen · 95 lines · 108 tokens per session scan A 938e38ca949d
fable-low-power is a skill published in the GitHub repository ussumant/useful-agent-skills (5 stars, last pushed 1mo ago), licensed MIT. It adds 108 tokens to every session and 1,287 once invoked, about $0.0005 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
offensive-c2-frameworks
Command and Control framework deployment, configuration, and operational tradecraft for red team engagements. Covers Cobalt Strike (malleable C2 profiles, Beacon types HTTP/HTTPS/DNS/SMB, Beacon Object Files for in-memory execution, sleep and jitter tuning, named pipe pivoting), Sliver (implant generation across…
offensive-crypto-attacks
Systematic methodology for identifying and exploiting cryptographic implementation weaknesses in real-world applications. Covers padding oracle attacks against CBC-mode ciphers with PKCS7 padding (Vaudenay's original attack through modern padbuster automation), ECB mode exploitation including block cut-and-paste and…
offensive-parameter-pollution
HTTP parameter pollution (HPP) checklist: duplicate parameter injection, backend vs frontend parsing differences, WAF bypass via HPP, server-side vs client-side HPP, and practical exploitation patterns. Use when testing web applications for parameter handling flaws.
offensive-wifi
Wireless / 802.11 attack methodology for red team engagements and wireless security assessments. Covers monitor-mode setup, WPA/WPA2-PSK handshake capture and PMKID attacks, WPA3 SAE downgrade and Dragonblood, WPA-Enterprise (EAP) attacks (MSCHAPv2 cracking, EAP-TLS cert theft, evil-twin RADIUS), Karma / Known Beacons…
offensive-z-wave
Z-Wave attack methodology — sniffing with Z-Force / EZ-Wave / RTL-SDR + ZniffMobile, S0 (legacy) network-key derivation flaw and key reuse, S2 (modern) ECDH commissioning analysis, replay/injection on unauthenticated nodes, default-key brute-force on test deployments, and home-automation hub pivots. Use when targeting…
seo
Optimize for search engine visibility and ranking. Use when asked to "improve SEO", "optimize for search", "fix meta tags", "add structured data", "sitemap optimization", or "search engine optimization".