Semantic-Anchors
A curated catalog of 230+ semantic anchors: well-defined terms like arc42, TDD London School or tracer bullet that activate deep, consistent knowledge in LLMs. Use them in prompts, skills and agent instructions instead of spelling out methods yourself.
Runssource: GitHubJavaScriptApache-2.0commit 1fd328552aae
JavaScript, Apache-2.0 licensed. The project labels itself: agentic coding, ai agents, claude code, llm and prompt engineering.
Semantic-Anchors runs. An Argusic agent installed it in 15 minutes and hit 5 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.
Website tests pass (22/22 files, 332/332 tests), production build completes (metadata extraction, docs rendering, vite build, prerendering, JSON-LD injection), and vite preview serves the site at HTTP 200 on /Semantic-Anchors/
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
Subject data from GitHub, linked at the top of this page. 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.
What went wrong, in the agent's own words
The agent's own words, worst first, never rewritten into advice.
- html-encoding-sniffer uses CJS require() on ESM-only @exodus/bytes package causing ERR_REQUIRE_ESM in vitest fork workers5 minutes
- Node system version 18.19.1 too old; all deps require Node 20+3 minutes
- @tailwindcss/oxide v4.2.1 missing linux-x64-gnu native binding on Node 182 minutes
- whatwg-url also uses CJS require() on @exodus/bytes ESM modules causing fork worker failures1 minute
- scripts/ tests fail: rolldown native binding for linux-x64-gnu not installed as optional dependency1 minute
- Install time
- 15 minutes
- Cold machine to finish
- 10 minutes
- Errors hit and fixed
- 5 hit, 5 fixed with no human help
- How the result was proved
- cd website && npm test: 22 test files passed, 332 tests passed. npm run build (root): full build completed (metadata extraction, docs rendering, vite build, prerendering, JSON-LD). vite preview + curl returned HTTP 200 on /Semantic-Anchors/
- Model tokens used
- 167,524
- Exact commit tested
- 1fd328552aae
- 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.
cd /work/repo/website && PATH="/tmp/node-v24.0.0-linux-x64/bin:$PATH" node -e "
const sniffer = require('"'./node_modules/html-encoding-sniffer/lib/html-encoding-sniffer.js');
const result = sniffer(new Uint8Array([0xef,0xbb,0xbf,0x68,0x69]));
console.log('BOM sniff UTF-8 =>', result);
const noBom = sniffer(new Uint8Array([0x68,0x69]));
console.log('No BOM =>', noBom);
\" 2>&1" in /work/repo
succeeded in 0ms:
BOM sniff UTF-8 => UTF-8
No BOM => windows-1252
tokens used
167,524Replay 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 5 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 Apache-2.0, as reported by its host.
What did not, or is not known
- Took 15 minutes to install, slower than the median of the 28 comparable projects Argusic has measured.
- Measured once so far. A single attempt shows it can run, not that it runs reliably.
Of the 29 agentic-coding projects Argusic has installed and timed, Semantic-Anchors was the 23rd fastest to reach a running state, and 21 of 29 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.
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
Topics (from GitHub)
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/semantic-anchors)Questions
- Does Semantic-Anchors run?
- Yes. Semantic-Anchors runs. Argusic installed and launched it on a clean machine in 15 minutes, hitting 5 errors on the way, and recorded the session.
- How did Argusic test Semantic-Anchors?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit 1fd328552aae. One attempt is recorded, and the full method is on the methodology page.
- What did it cost to test Semantic-Anchors?
- The run that produced this verdict cost $0.35: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does Semantic-Anchors take to install?
- 15 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 Semantic-Anchors need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing Semantic-Anchors?
- 5 things broke in the recorded run, and 5 were fixed without human help. Each one, and the time it cost, is listed on this page.
- How does Semantic-Anchors compare with the alternatives?
- Of the 29 agentic-coding projects Argusic has installed and timed, Semantic-Anchors was the 23rd fastest to reach a running state, and 21 of 29 reached one at all.
- Where is the evidence for Semantic-Anchors?
- 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.