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/drmahdikazempour/agent-stack/stack-measurenpx skills add drmahdikazempour/agent-stack --skill stack-measuregit clone --depth 1 https://github.com/drmahdikazempour/agent-stackWhat 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 | $0.00074 | $0.00263 |
| Opus 5 | $0.00037 | $0.00131 |
| Sonnet 5 | $0.00015 | $0.00053 |
| Haiku 4.5 | $0.00007 | $0.00026 |
Grade A, and why
stack-measure 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.
What it actually says
stack-measure
Quantify token usage with the neutral ccusage tool. Savings are always measured, never claimed.
What to do
- Baseline:
npx @drmahdikazempour/agent-stack measure(init already stored one in.agent-stack/baseline.json). - Compare:
npx @drmahdikazempour/agent-stack measure --since 7d— reports baseline vs recent average input tokens/day and the % reduction, color-coded against the ≥40% target.
Notes
- If
ccusageisn't installed, the command falls back to the localusage.jsonlourStophook appends; installccusage(npm i -g ccusage) for authoritative numbers. - Telemetry-free and local-only: it reads ccusage's JSONL on the user's machine.
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 · 17 lines · 74 tokens per session scan A 4cf8b59b4152
stack-measure is a skill published in the GitHub repository drmahdikazempour/agent-stack (2 stars, last pushed 3mo ago), licensed MIT. It adds 74 tokens to every session and 263 once invoked, about $0.0004 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
github-secret-hunting
Find leaked API keys, tokens, and credentials in public GitHub repositories.
tokf-filter
This skill should be used when the user asks to "create a filter", "write a tokf filter", "add a filter for ", "how do I filter output", or needs guidance on tokf filter step types, templates, pipes, or placement conventions.
tokf-discover
Find missed token savings in Claude Code sessions and create filters for unfiltered commands.
tokf-discover
Find missed token savings by scanning AI coding session files for commands that ran without tokf filtering.
dingtalk_channel_connect
使用可视浏览器自动完成 CoPaw 的钉钉频道接入。适用于用户提到钉钉、DingTalk、开发者后台、Client ID、Client Secret、机器人、Stream 模式、绑定或配置 channel 的场景；支持遇到登录页时暂停，等待用户登录后继续。.
linggen
Linggen — durable cross-host memory plus browser control, over two local MCP servers: ling-mem for memory, the Linggen engine for browser, X and agents. Memory: three-tier model (core + long-term + episodic staging) of who the user is, not a log of what was done; same ling-mem daemon and store in Claude Code, Codex…