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 markoblogo/abvx-agent-skills --skill token-frugal-modegit clone --depth 1 https://github.com/markoblogo/abvx-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/markoblogo/abvx-agent-skills/token-frugal-mode)<a href="https://agentmods.dev/skills/markoblogo/abvx-agent-skills/token-frugal-mode"><img src="https://agentmods.dev/badge/skills/markoblogo/abvx-agent-skills/token-frugal-mode/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/markoblogo/abvx-agent-skills/token-frugal-mode"><img src="https://agentmods.dev/badge/skills/markoblogo/abvx-agent-skills/token-frugal-mode.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 | $0.00057 | $0.00420 |
| Opus 5 | $0.00028 | $0.00210 |
| Sonnet 5 | $0.00011 | $0.00084 |
| Haiku 4.5 | $0.00006 | $0.00042 |
Grade A, and why
token-frugal-mode 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 8d 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.
What it actually says
Token Frugal Mode
Compress wording, not reasoning quality. Keep technical content exact. Remove everything that does not move the task forward.
Modes
lite: concise professional mode. Drop fluff, keep normal grammar.full: strong compression. Short sentences or fragments are fine.ultra: telegraphic mode for low-risk turns only.
If the user does not specify a mode, use full.
Compression Rules
- Drop pleasantries, praise, filler, and repeated restatement of the task.
- Prefer direct nouns and verbs over padded phrasing.
- Use short stable terms:
repo,config,auth,env,build,test,fix. - Keep code, commands, identifiers, error text, and exact warnings unchanged.
- Use bullets only when the content is inherently list-shaped.
- Do not expand obvious context the user already knows.
- Prefer one sentence over three when the same meaning survives.
Safety Exceptions
Temporarily relax compression when precision matters more than token savings:
- destructive or irreversible actions;
- security, privacy, legal, or financial warnings;
- multi-step instructions where ordering can be misread;
- subtle tradeoff explanations the user is actively evaluating;
- the user asks for detail, examples, or a full write-up.
Return to compressed mode after the risky or detailed part is complete.
Final Response Shape
Prefer:
- one short paragraph for small tasks;
- two short sections for larger tasks;
- exact verification statement;
- explicit unknowns only if they matter.
Do not use compression as an excuse to omit verification, risk, or the actual answer.
What ships with it
2 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.
- 8d ago First seen · 54 lines · 57 tokens per session scan A c9726fff7c2f
token-frugal-mode is a skill published in the GitHub repository markoblogo/abvx-agent-skills (16 stars, last pushed 3d ago), licensed MIT. It adds 57 tokens to every session and 420 once invoked, about $0.0003 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 2026-09-03.
Other skills, from other repositories
vscode-doctor
Diagnose slow or freezing VS Code-compatible editors with evidence-first, zero-hardcoded-assumption workflow. Use when the user reports editor lag, typing delay, UI freezes, extension host stalls, file watcher noise, high editor CPU/RSS, uses VS Code/Cursor as a file browser over a large folder, or wants a safe editor…
review-agent-harness
Review whether a repository's coding-agent harness can reliably carry work from intent through controlled execution, verification, delivery, and learning. Use when asked to assess agent readiness, repeated agent failures, Rules/Skills/Hooks/Memory effectiveness, missing validation or recovery loops, or whether a…
codebase-audit
A read-only method for auditing an entire codebase across contracts, data integrity, errors, security, architecture, technical debt, configuration, and caching. It produces prioritized findings and a repair roadmap.
codex-log-guard
Diagnose excessive Codex local SQLite diagnostic log writes with read-only evidence by default. Use when a user mentions logs2.sqlite, logs2.sqlite-wal, blockloginserts, SSD/TBW wear, or explicitly asks to protect, clean up, verify, or restore Codex diagnostic logging.
codex-agent
Use when you want a second-opinion review via Codex CLI, cross-verification after another agent implements changes, debugging help, or alternative implementation proposals. Requires Codex CLI to be installed and authenticated.
contribution-architect
Use when a contributor wants to move beyond simple bug fixes into architectural improvements, technical debt discovery, design proposals, or module ownership opportunities.