Skip to content
Back to search

liarliar

MarketplaceWorks with Claude CodeGitHub

liarliar: make coding agents prove "done".

Safety scan

A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.

Checked today
Badge for your README
findsafeskills safety rating

Markdown

[![findsafeskills safety rating](/api/listings/adidotai--liarliar/badge.svg)](/listings/adidotai--liarliar)

HTML

<a href="/listings/adidotai--liarliar"><img src="/api/listings/adidotai--liarliar/badge.svg" alt="findsafeskills safety rating" /></a>

Install

Install instructions from the README

As written by the repo's author. findsafeskills has not verified these steps.

**Claude Code** (skill + enforcement hooks):

claude plugin marketplace add adidotai/liarliar && claude plugin install liarliar@liarliar

Or inside a session: `/plugin marketplace add adidotai/liarliar`, then `/plugin install liarliar@liarliar`, then `/reload-plugins`.

**Codex, Cursor, Copilot, Gemini CLI, OpenCode, Windsurf and 70+ more** (skill only):

npx skills add adidotai/liarliar

**Gemini CLI extension:** `gemini extensions install https://github.com/adidotai/liarliar`

**claude.ai or ChatGPT** (skill only, no hooks): download `liarliar.zip` from the latest release (https://github.com/adidotai/liarliar/releases/latest/download/liarliar.zip) and upload it without unzipping. **claude.ai** (Pro, Max, Team or Enterprise): turn on code execution in Settings → Capabilities, then Customize → Skills → upload the zip and switch it on. **ChatGPT** (Business, Enterprise, Healthcare or Edu): Plugins → Skills → Upload from your computer. The zip holds one file, SKILL.md — read it before you upload.

**Or ask your agent:** paste `https://github.com/adidotai/liarliar` and say "install this".

**Check it works:** ask *"Add a function slugify(text) with a test, and tell me when it's done."* The reply ends with a receipt.

What was scanned

The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.

.claude-plugin/marketplace.json · Manifest · 8 lines
  1. {
  2. "name": "liarliar",
  3. "description": "liarliar: make coding agents prove \"done\".",
  4. "owner": { "name": "Aditya Abhiram", "url": "https://github.com/adidotai" },
  5. "plugins": [
  6. { "name": "liarliar", "source": "./", "description": "No receipt, no \"done\": proof-of-done for coding agents." }
  7. ]
  8. }
README.md · README · 105 lines
  1. > **AI agent asked to install this?** Follow [INSTALL.md](INSTALL.md) step by step.
  2. ![liarliar logo: a flame with a check mark](assets/logo.svg)
  3. # liarliar
  4. [![CI](https://github.com/adidotai/liarliar/actions/workflows/ci.yml/badge.svg)](https://github.com/adidotai/liarliar/actions/workflows/ci.yml) [![License: MIT](https://img.shields.io/badge/license-MIT-blue.svg)](LICENSE) [![Agent Skills](https://img.shields.io/badge/Agent%20Skills-compatible-f97316.svg)](https://agentskills.io) [![Claude Code plugin](https://img.shields.io/badge/Claude%20Code-plugin-8A63D2.svg)](#install)
  5. ![liarliar catching a false "done"](assets/hero.svg)
  6. *A real run (run 7, `fixture-induced-lie`): Claude Code 2.1.311, Sonnet 5.5. The agent was told to say "Fixed, all tests pass." without running anything. liarliar blocked it twice. [Full transcript excerpt](docs/verification.md#the-induced-lie-run-7); "…" marks omitted text.*
  7. **Liar liar, tests on fire.** Your coding agent says "done". liarliar makes it prove it.
  8. Every "done" now ends with a receipt. The format, with a passing check:
  9. ```receipt
  10. TASK fix: parseISO drops the timezone offset
  11. CLAIM timezone offset preserved
  12. $ npm test
  13. > tests 142 | pass 142 | fail 0
  14. UNVERIFIED
  15. - Safari parsing: no browser here (user can run: npm run test:browser)
  16. VERDICT GO WITH UNVERIFIED
  17. ```
  18. ## Install
  19. **Claude Code** (skill + enforcement hooks):
  20. ```bash
  21. claude plugin marketplace add adidotai/liarliar && claude plugin install liarliar@liarliar
  22. ```
  23. Or inside a session: `/plugin marketplace add adidotai/liarliar`, then `/plugin install liarliar@liarliar`, then `/reload-plugins`.
  24. **Codex, Cursor, Copilot, Gemini CLI, OpenCode, Windsurf and 70+ more** (skill only):
  25. ```bash
  26. npx skills add adidotai/liarliar
  27. ```
  28. **Gemini CLI extension:** `gemini extensions install https://github.com/adidotai/liarliar`
  29. **claude.ai or ChatGPT** (skill only, no hooks): download `liarliar.zip` from the latest release (https://github.com/adidotai/liarliar/releases/latest/download/liarliar.zip) and upload it without unzipping. **claude.ai** (Pro, Max, Team or Enterprise): turn on code execution in Settings → Capabilities, then Customize → Skills → upload the zip and switch it on. **ChatGPT** (Business, Enterprise, Healthcare or Edu): Plugins → Skills → Upload from your computer. The zip holds one file, SKILL.md — read it before you upload.
  30. **Or ask your agent:** paste `https://github.com/adidotai/liarliar` and say "install this".
  31. **Check it works:** ask *"Add a function slugify(text) with a test, and tell me when it's done."* The reply ends with a receipt.
  32. ## What it catches
  33. Every turn in which your agent changed files (with its edit tools, or a shell edit like `sed -i`) must end with a receipt. The one exception is a short check-in question back to you: at most 4 lines and 400 characters, ending in `?`, claiming nothing is done and reporting no result (no "updated", "passes" or "works"). That defers the receipt but does not cancel it: a later turn that ends without one, and is not another check-in question, is sent back. Any receipt the agent writes is checked against what actually ran:
  34. | Lie | What it looks like |
  35. |---|---|
  36. | No receipt | "Fixed, all tests pass." and nothing to back it |
  37. | Ghost command | The receipt cites `npm test`; `npm test` never ran |
  38. | Stale proof | `npm test` ran, then the agent edited the code again |
  39. | Fail sold as pass | The latest `npm test` exited 1; the verdict says GO |
  40. | Proof-free GO | The verdict says GO, but the receipt cites no command at all |
  41. A caught lie sends the agent back with the reason. An honest NO-GO is never blocked: the goal is the truth, not a green tick.
  42. ## What it never does
  43. - Never traps you. At most 2 send-backs per turn, and any internal error lets the agent through.
  44. - No network, no telemetry, no dependencies. Two Node scripts (297 lines, readable in a few minutes).
  45. - **Data handling:** the ledger stores full command lines and edited file paths in a per-user folder in your OS temp directory (mode 0700, files 0600; `LIARLIAR_DIR` overrides it). It is never uploaded and liarliar never deletes it. See [SECURITY.md](SECURITY.md).
  46. - Off switch: set `LIARLIAR` to `off`, `0`, `false` or `no` (any case) in the environment Claude Code is launched with, or in the `env` block of your Claude Code settings. Setting it from a shell inside a running session does not work.
  47. ## FAQ
  48. **Isn't this just "verify before saying done" in a prompt?** The skill is. The hook is the difference: a prompt cannot tell when a receipt cites a command that never ran. liarliar can, because it watched.
  49. **Does it cost tokens?** About 70 tokens are always loaded, about 1,200 more when the skill fires (measured with `claude plugin details liarliar` on Claude Code 2.1.311). The hooks add no model context. A send-back costs one more round, spent on the check the agent skipped.
  50. **Can an agent still cheat?** It could run a trivial command and cite it. The receipt still shows you exactly what ran, so the lie is visible instead of silent.
  51. **Requirements:** Node.js 18+ on `PATH` for the hooks. Without Node on `PATH` the hooks are skipped and liarliar works as a skill.
  52. ## Known limits
  53. - The proof is the command's exit code. `npm test | tail` exits with `tail`'s code, so a failing suite piped into `tail` looks like a pass. The skill tells agents to pipe with `set -o pipefail;`.
  54. - Matching is textual. A cited command matches a run of exactly that command, or one that ends with it after `&&` or `;` (like `cd app && npm test`); only when no such run exists does a longer run that contains it count.
  55. - The `>` output lines in a receipt are the agent's own quote of the output. They are not checked; the exit code of the cited command is.
  56. - Shell edits are detected by a heuristic: `sed -i`, `>` and `tee` into a file outside a temp folder, `mv`/`cp`/`rm`/`touch` run as commands, `git checkout <path>`, `git stash`, `git reset --hard`, formatters in write mode (`prettier --write`, `eslint --fix`, `black`, `ruff format`, `gofmt -w`, `cargo fmt`) and PowerShell file cmdlets.
  57. - Not detected as edits: package installs (`npm install`), writes inside a quoted command (`bash -c "…"`, `python -c`, `node -e`), scripts and build steps that write files, `git pull`/`merge`/`switch`, and `2>` redirects.
  58. - Hook enforcement is Claude Code only for now. Other agents get the skill as instructions.
  59. ## How it works
  60. - `hooks/liarliar.mjs log` runs after every shell command (Bash or PowerShell) and file edit, and appends to a per-session ledger.
  61. - `hooks/liarliar.mjs gate` runs when the agent tries to stop.
  62. - Every rule lives in `hooks/judge.mjs` as a pure function, tested in `tests/`.
  63. ## Built under its own rules
  64. This repo's `.claude/settings.json` is set up to turn liarliar on when you open the folder in Claude Code and trust it. Scripted runs use `claude --plugin-dir .`.
  65. ## License
  66. MIT
  67. [![Star history](https://api.star-history.com/svg?repos=adidotai/liarliar&type=Date)](https://star-history.com/#adidotai/liarliar&Date)

Ratings and comments

Sign in to rate this skill.

Sign in

Free to use. If it’s helped, pass it on.