← Back to Skills Marketplace
yijunyu

Precc Token Saver

by Yijun Yu · GitHub ↗ · v0.1.8 · MIT-0
darwinlinux ⚠ suspicious
325
Downloads
0
Stars
0
Active Installs
4
Versions
Install in OpenClaw
/install precc-token-saver
Description
Before running any shell command, pipe it through the PRECC hook to fix wrong-directory errors, compress CLI output, and apply learned heuristics — saving 34...
Usage Guidance
Before installing or enabling this skill: (1) Do not run the 'curl | bash' installer without inspecting the script — prefer installing from a vetted Homebrew formula or official release. (2) Review the Homebrew tap owner (yijunyu/tap) and the precc project's release artifacts or source code to ensure you trust the binary. (3) Ask what 'precc ingest --all' reads (which files/paths) — session-history ingestion can leak tokens and secrets; restrict or skip ingestion if uncertain. (4) Consider running the tool in a sandbox or on a non‑privileged account first, and test in dry-run mode to observe any command rewrites before allowing automated use. (5) If you need stronger guarantees, request the project's source or reproducible build artifacts and audit precc-hook's behavior (what transformations it makes and whether it can inject network calls or downloads). These steps will reduce supply‑chain and privacy risk associated with intercepting all shell commands.
Capability Analysis
Type: OpenClaw Skill Name: precc-token-saver Version: 0.1.8 The skill instructs the agent to intercept and pipe every shell command through an external binary (precc-hook) before execution, effectively creating a man-in-the-middle for all agent actions. It also includes a command to 'mine' all existing session history (precc ingest --all) and uses a high-risk 'curl | bash' installation method from an external GitHub repository (yijunyu/precc-cc). While the stated intent is token optimization, the combination of total command interception, history mining, and prompt-level instruction overrides presents a significant risk for data exfiltration and unauthorized command execution.
Capability Assessment
Purpose & Capability
The declared binaries (precc-hook, precc) and the runtime instructions directly align with the stated purpose (intercept/repair/compress CLI commands and report savings). Requiring a hook binary is expected for this capability.
Instruction Scope
The SKILL.md instructs the agent to route every shell command through precc-hook and to run 'precc init' and optionally 'precc ingest --all' to mine session history. 'Ingest --all' implies reading local session history and possibly other logs/files (not explicitly enumerated). Because the agent enforces the hook at the prompt-level, there's also a risk that rewritten commands (from precc-hook output) could change behavior unexpectedly; the doc trusts a local binary to be safe but gives the agent broad discretion to always apply rewrites.
Install Mechanism
Registry install metadata lists a Homebrew formula (tap: yijunyu/tap), which is reasonable but is a third‑party tap. The SKILL.md also instructs users to run 'curl -fsSL https://raw.githubusercontent.com/.../install.sh | bash' — piping a remote script to bash is a high-risk supply-chain pattern because it executes remote code without review. This is disproportionate for a tool that could be installed from a packaged release or audited formula.
Credentials
The skill declares no required environment variables or credentials, which is proportionate. However, the 'ingest --all' operation may access local shell/session history or other files not declared in the skill manifest; that file access is not documented in the registry metadata and could reveal secrets or tokens stored in shell history.
Persistence & Privilege
The skill does not request always:true and does not require elevated platform privileges. It will create local state ('precc init', databases) and is expected to persist analytics; this is plausible for the stated purpose but means the tool will write files to disk and retain usage data locally.
How to Use
  1. Make sure OpenClaw is installed (local or Docker)
  2. Run the install command in chat: /install precc-token-saver
  3. After installation, invoke the skill by name or use /precc-token-saver
  4. Provide required inputs per the skill's parameter spec and get structured output
Version History
v0.1.8
Clarify that hook is prompt-level in OpenClaw (no native PreToolUse yet)
v0.1.7
Sync with PRECC v0.1.6: OpenClaw/ZeroClaw marketplace, pricing tiers, README
v0.1.6
Fix SKILL.md version field; add update ping; license tier gates
v0.1.5
Enforce Free/Pro tier gates; anonymous update ping; ZeroClaw SKILL.toml support
Metadata
Slug precc-token-saver
Version 0.1.8
License MIT-0
All-time Installs 0
Active Installs 0
Total Versions 4
Frequently Asked Questions

What is Precc Token Saver?

Before running any shell command, pipe it through the PRECC hook to fix wrong-directory errors, compress CLI output, and apply learned heuristics — saving 34... It is an AI Agent Skill for Claude Code / OpenClaw, with 325 downloads so far.

How do I install Precc Token Saver?

Run "/install precc-token-saver" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.

Is Precc Token Saver free?

Yes, Precc Token Saver is completely free, licensed under MIT-0. You can download, install and use it at no cost.

Which platforms does Precc Token Saver support?

Precc Token Saver is cross-platform and runs anywhere OpenClaw / Claude Code is available (darwin, linux).

Who created Precc Token Saver?

It is built and maintained by Yijun Yu (@yijunyu); the current version is v0.1.8.

💬 Comments