meta-llm-charter

Compact operational charter that turns LLM coding agents into disciplined principal engineers. Eleven rules + one meta-rule.

Runssource: GitHubTypeScriptMITcommit 7a814b1152ae

TypeScript, MIT licensed. The project labels itself: ai, ai agents, claude, coding agents, constitution, cursor, frontier ai and llm.

meta-llm-charter runs. An Argusic agent installed it in 8 minutes and hit 3 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.

The eval harness installs and builds cleanly, all 70 harness unit tests pass, all 15 fixture suites match their pinned counts, and a documented bug fix plus the --quiet task implemented over the fixture verified green test runs and correct CLI output in this container.

What the agent ended up with on a clean machine, in its own words. How this is measured

Measured by Argusic on a fresh machine every time. Every number links to its evidence. Argusic Score 100 of 100 (the mean of this project's run scores).

At a glance

verdict
Runs
Argusic Score
100 / 100
cost of the verifying run
$0.04 (measured)
recorded runs
1
last tested
stars
247
forks
18
open issues
0
watchers
1
size
0 MB
created
last push

Subject data from GitHub, linked at the top of this page, refreshed . Test data by Argusic (CC BY 4.0); every number links to a run page with the full log, the recording, and their sha256 hashes.

What was measured

From the run that decided this verdict. Every line is a recorded value, not an estimate.

Time lost to each failure while testing meta-llm-charter, drawn from the recorded run
Every bar is a failure the agent recorded, with the time it cost. Drawn from this run, not from anywhere else.

What went wrong, in the agent's own words

The agent's own words, worst first, never rewritten into advice.

  • fixture-local 'npm test' (node --import tsx) fails on container's Node 18.19.1: ERR_MODULE_NOT_FOUND for tsx; README/CI require Node 20+, canonical harness command is npx --yes tsx --test2 minutes
  • npm audit reported 1 high severity advisory after install (no install failure)
  • Full eval path 'npm start' cannot run: ANTHROPIC_API_KEY missing (harness abort by design), no docker binary/daemon available to build the sandbox image
Install time
8 minutes
Cold machine to finish
4 minutes
Errors hit and fixed
3 hit, 3 fixed with no human help
How the result was proved
npm run test:harness exited 0 (70 tests, 70 pass); npm run fixtures:check exited 0 (15 fixtures, 0 failures, 0 unpinned); npm run build exited 0; fixture 02 repair: npx --yes tsx --test test/format.spec.ts -> pass 9 fail 0 and formatCurrency(null) -> '$0.00'; fixture 09 --quiet implementation: 9/9 pass and CLI printed only '6 records, 2 errors'
Model tokens used
229,269
Exact commit tested
7a814b1152ae
Container image
sha256:cdd920bce783

What was not measured

The other half, so you can see exactly how far this evidence goes. A gap is printed as a gap and never filled in.

Peak GPU memory
this ran on a CPU machine, so there was no GPU to sample
Behaviour over a long run
each attempt uses the smallest documented settings and a fixed time budget, so this measures whether it runs, not how it holds up under load

The end of the recording

The last lines of the terminal session that decided this verdict, exactly as they were recorded.

**Installed & built**
- `npm install` in `evals/` — exit 0, added 47 packages (1 high-severity audit advisory, nothing fa…
- `npm run build` (`tsc`) — exit 0, 18 compiled JS files in `evals/dist/`.
**Tests run (all real, exit 0)**
- `npm run test:harness` — `# tests 70, # pass 70, # fail 0`.
- `npm run fixtures:check` — discovered 15 fixtures, `0 failure(s), 0 unpinned notice(s)`; per-fixt…
- Directly executed fixture suites and a repair check: applying fixture 02's documented bug fix tur…
**Errors & repairs**
- Node 18 vs fixture-local `npm test` (`node --import tsx`): that script can't resolve `tsx` on Nod…
- Real `npm start` path: blocked by `ANTHROPIC_API_KEY is required` (harness's own guard fired as d…
**Verification summary**
- `npm run build` exit 0; `npm run test:harness` 70/70 pass; `npm run fixtures:check` 15/15 match. …

Replay the whole session, every command from a clean machine to this point.

How it was tested

One agent, one container, no human help. It installs the project the way its own documentation says to, runs it, and fixes what breaks. Everything below is recorded as it happened: the terminal session, the log and the exact commit. The full method.

Strengths and limits

Measured facts, not opinions. How this is written.

What went well

  • Reached a running state on a clean machine, with the session recorded.
  • Recovered from all 3 errors without a human stepping in, which says the failures are documented well enough to solve.
  • Ran without a GPU, so it does not need one to start.
  • Licensed MIT, as reported by its host.

What did not, or is not known

  • Took 8 minutes to install, slower than the median of the 236 comparable projects Argusic has measured.
  • Measured once so far. A single attempt shows it can run, not that it runs reliably.

Of the 237 ai projects Argusic has installed and timed, meta-llm-charter was the 156th fastest to reach a running state, and 168 of 237 reached one at all.

What it is a reasonable choice for

  • Trying it on a laptop or a small server: it reached a running state without a GPU.
  • A quick evaluation: it was running 8 minutes after the clone.

Also tested, in the same area

Every one of these was installed and run by Argusic on a clean machine. Nothing appears here that was not tested.

Run history

tested byattemptoutcomescorecost USDwhen
Argusic Runner1/3Runs100.000.04

Topics (from GitHub)

aiai-agentsclaudecoding-agentsconstitutioncursorfrontier-aillmllm-agentsprompt-engineering

Embed the badge

Markdown for the project README. It links back here; terms on the terms page.

[![Tested by Argusic](https://argusic.com/badge/meta-llm-charter.svg)](https://argusic.com/subject/meta-llm-charter)

Questions

Does meta-llm-charter run?
Yes. meta-llm-charter runs. Argusic installed and launched it on a clean machine in 8 minutes, hitting 3 errors on the way, and recorded the session.
How did Argusic test meta-llm-charter?
On a fresh, disposable machine, with every command recorded and the repository pinned at commit 7a814b1152ae. One attempt is recorded, and the full method is on the methodology page.
What did it cost to test meta-llm-charter?
The run that produced this verdict cost $0.04: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
How long does meta-llm-charter take to install?
8 minutes in the run that decided this verdict, from a clean machine to a running state. That is one measured attempt, not an average.
Does meta-llm-charter need a GPU?
Not to start. Argusic reached a running state on a machine with no GPU.
What goes wrong when installing meta-llm-charter?
3 things broke in the recorded run, and 3 were fixed without human help. Each one, and the time it cost, is listed on this page.
How does meta-llm-charter compare with the alternatives?
Of the 237 ai projects Argusic has installed and timed, meta-llm-charter was the 156th fastest to reach a running state, and 168 of 237 reached one at all.
Where is the evidence for meta-llm-charter?
The recorded run is on this page, each linking to its full log and terminal recording, stored with a sha256 fingerprint so it cannot be quietly altered.

Discussion