Agent skill

Savings

by daseinlabs in daseinlabs/parsec

Show measured token savings — re-reads blocked and command loops broken by the parsec no-reread hook, from the local ledger, never estimated.

MITAuto-check passed

Install Savings

skills CLI
$ npx skills add daseinlabs/parsec --skill savings -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install daseinlabs/parsec savings --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/daseinlabs/parsec.git skills-src && mkdir -p .claude/skills && cp -r skills-src/packages/plugin/skills/savings .claude/skills/savings && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
savings
GitHub stars
135
Token cost
~273 tokens
SKILL.md length
136 words
Files
1
Skills in repo
8
Repo updated
First seen
Licence
MIT

At a glance

Show measured token savings — re-reads blocked and command loops broken by the parsec no-reread hook, from the local ledger, never estimated.

  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Savings is an agent skill from daseinlabs/parsec. Show measured token savings — re-reads blocked and command loops broken by the parsec no-reread hook, from the local ledger, never estimated.

Its SKILL.md is about 270 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

The repository describes itself as: Agent runtime optimization with Small Language Models. The licence is MIT.

Example prompts

  • “/savings”

What it can do on your machine

Read from SKILL.md and the folder at commit e97063c. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Savings loads about 273 tokens when it runs. Until then it costs about 37 tokens; SKILL.md has 136 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~37
When it runs · the whole SKILL.md, loaded when a task matches
~273

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from daseinlabs/parsec at commit e97063c, republished under its MIT licence (© daseinlabs). 136 words, ~273 tokens.

Download SKILL.mdSave it as .claude/skills/savings/SKILL.md (or your agent's skills folder).
name
savings
description
Show measured token savings — re-reads blocked and command loops broken by the parsec no-reread hook, from the local ledger, never estimated.

Run ${CLAUDE_PLUGIN_ROOT}/bin/parsec savings and present its output to the user conversationally. Every number in that report is measured — proxy rows are the per-request count_tokens counterfactual vs actually-billed usage, hook rows are blocked re-reads x the on-disk bytes of the denied range; if the report says the ledger is empty, say so plainly — never estimate or extrapolate savings. The report is grouped by requests, conversations, and Claude Code sessions where the ledger has session identity.

If the user asks about the live status line: parsec setup writes a managed statusLine entry into ~/.claude/settings.json automatically (plugins cannot ship the key themselves) and never overwrites one the user already has. If they want it back after removing it, rerunning parsec setup — or just starting a new session — re-adds it; parsec disable removes it along with the other managed keys.

© daseinlabs, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in packages/plugin/skills/savings of daseinlabs/parsec.

Open the folder on GitHubat commit e97063c

Compare with similar skills

Savings next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Savings compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Savings this skilldaseinlabs/parsec135—~273Automated safety check: PassMIT
Block Kitopenclaw/openclaw392k—~624Automated safety check: PassMIT
Render Blockingthedaviddias/Front-End-Checklist74k—~430Automated safety check: PassMIT
Blocking IO Guardbytedance/deer-flow84k—~1.7kAutomated safety check: PassMIT
Color Blockingsickn33/agentic-awesome-skills47k1 repos~2.4kAutomated safety check: PassMIT
Add Block Previewsimstudioai/sim30k—~1.3kAutomated safety check: PassApache-2.0

Similar skills

  • Block Kit

    openclaw/openclaw

    Use proactively for structured or interactive Slack replies, and when asked to author or validate native Slack Block Kit JSON.

    392k GitHub stars~624 tokensUpdated today
    Auto-check passed
  • Render Blocking

    thedaviddias/Front-End-Checklist

    A skill your agent uses when auditing slow page loads, heavy assets, or rendering delays related to Eliminate render-blocking resources.

    74k GitHub stars~430 tokensUpdated 4 days ago
    Frontend & DesignAuto-check passed
  • Blocking IO Guard

    bytedance/deer-flow

    Adds a runtime test anchor for backend async code that could block the asyncio event loop, and proves the anchor fails when the blocking call returns.

    84k GitHub stars~1.7k tokensUpdated today
    DevelopmentAuto-check passed
  • Color Blocking

    sickn33/agentic-awesome-skills

    Web and App implementation guide for Color Blocking. An agent skill from sickn33/agentic-awesome-skills.

    47k GitHub starsUsed in 1 repo~2.4k tokens
    MobileAuto-check passed
  • Add Block Preview

    simstudioai/sim

    Gate a block's visibility — ship an unreleased block as a preview (hidden until revealed via AppConfig/env), reveal it to admins/orgs, GA it, or kill-switch a shipped block

    30k GitHub stars~1.3k tokensUpdated today
    Auto-check passed
  • Measure Before You Fix

    garrytan/gbrain

    Before fixing a slow/stale/timeout alert, measure the step yourself.

    31k GitHub stars~2.5k tokensUpdated yesterday
    Productivity & AutomationAuto-check passed

More from daseinlabs/parsec

All 8 skills in this repo
  • Desktop

    daseinlabs/parsec

    Route Claude Desktop's Cowork / Agent-mode traffic through the local parsec proxy so it gets curation and savings too.

    135 GitHub stars~1.5k tokensUpdated 5 days ago
    Auto-check passed
  • Login

    daseinlabs/parsec

    Sign in to Parsec so token savings show up in the user's dashboard.

    135 GitHub stars~502 tokensUpdated 5 days ago
    Auto-check passed
  • Setup

    daseinlabs/parsec

    Activate parsec — write the Claude Code routing env (ANTHROPICBASEURL → local proxy), install the savings status line, and start the proxy.

    135 GitHub stars~549 tokensUpdated 5 days ago
    Auto-check passed
  • Trim

    daseinlabs/parsec

    Stage a det+dir compaction of this session — a deterministic needed-set trim of the transcript plus a standing-directives block, injected automatically after /clear.

    135 GitHub stars~751 tokensUpdated 5 days ago
    Auto-check passed
  • Proxy

    daseinlabs/parsec

    Restart the local parsec proxy if it was killed mid-session — brings the supervisor back on the routed port so requests stop failing.

    135 GitHub stars~382 tokensUpdated 5 days ago
    Auto-check passed
  • Uninstall

    daseinlabs/parsec

    Cleanly remove parsec from this machine — undo Claude Code routing, stop the local proxy, delete downloaded models and data, then uninstall the plugin itself.

    135 GitHub stars~491 tokensUpdated 5 days ago
    Auto-check passed

Questions about Savings

What does Savings do?

Show measured token savings — re-reads blocked and command loops broken by the parsec no-reread hook, from the local ledger, never estimated. Savings is an agent skill from daseinlabs/parsec. Show measured token savings — re-reads blocked and command loops broken by the parsec no-reread hook, from the local ledger, never estimated.

How do I install Savings in Claude Code?

Run `npx skills add daseinlabs/parsec --skill savings -a claude-code`. Or copy the skill folder (packages/plugin/skills/savings in daseinlabs/parsec) into .claude/skills/savings in your project. Claude Code loads it when a task matches its description.

How do I install Savings in Codex?

Run `npx skills add daseinlabs/parsec --skill savings -a codex`. Or copy the skill folder (packages/plugin/skills/savings in daseinlabs/parsec) into .agents/skills/savings in your project. Codex loads it when a task matches its description.

Can I use Savings in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add daseinlabs/parsec --skill savings -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/savings, .gemini/skills/savings, .github/skills/savings and .opencode/skills/savings in your project.

What does Savings need to run?

SKILL.md names no scripts, command-line tools or credentials: Savings is instructions for the agent only.

Does Savings access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Savings safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Savings use?

Savings is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Savings use?

About 273 tokens (SKILL.md is roughly 1.1k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Savings?

Skills that share tags, products or a category with Savings: Block Kit (openclaw/openclaw, 392k stars), Render Blocking (thedaviddias/Front-End-Checklist, 74k stars), Blocking IO Guard (bytedance/deer-flow, 84k stars) and Color Blocking (sickn33/agentic-awesome-skills, 47k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Savings?

daseinlabs (a GitHub organization) maintains it in daseinlabs/parsec, which has 135 GitHub stars. The repository holds 8 skills in this directory. The repository was last updated on October 6, 2026.

Source: daseinlabs/parsec on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.