STE Audit
Audit text against ASD-STE100 (Issue 9, January 2025). A memory line or
writer skill sets the style; this verifies it, with rule numbers and
quotes.
Scope: structural rules only. Dictionary rules (1.2, 1.3: approved words,
approved meanings) need the STE dictionary, which is ASD copyright and not
bundled here. Free copy: request form on asd-ste100.org.
Modes
- Procedural (instructions to act): 20 words max per sentence.
- Descriptive (everything else): 25 words max per sentence.
- Ambiguous sentence: judge at 25 and mark it in the row.
Method
- Collect the assistant's responses in order, or a file the user names.
Exempt from all checks: code blocks, commands, file paths, URLs, quoted
error text.
- Split into sentences and paragraphs. Words are whitespace tokens; a
hyphenated word counts as one.
- Check each sentence against the table.
- Report every violation: verbatim quote + rule number.
- Trend violations per response, first to last.
- Verdict, drift start point, worst sentence.
Checks
| rule |
violation to flag |
| 5.1 |
procedural sentence over 20 words |
| 6.3 |
descriptive sentence over 25 words |
| 6.6 |
paragraph with more than six sentences |
| 6.5 |
paragraph covering more than one topic (judgment call: name both topics) |
| 2.1 |
multi-word noun (noun cluster) longer than three words |
| 3.2 |
verb form outside: infinitive, imperative, simple present, simple past, simple future, past participle as adjective |
| 3.4 |
stacked auxiliary constructions ("would have been configured") |
| 3.5 |
an -ing verb used outside a technical-noun role |
| 3.6 |
passive voice where the agent is known |
Report
| where | quote | rule | violation |
|---|---|---|---|
| r4 s2 | "the config that was being generated by the daemon" | 3.6 | passive, agent known |
| r7 s1 | 31 words | 6.3 | descriptive cap is 25 |
| r7 s4 | "long running background task execution queue" | 2.1 | five-word noun cluster |
| r9 s3 | "consider leveraging incremental checkpointing" | 3.5 | -ing verb, not a technical noun |
| response | sentences | violations | rate |
|---|---|---|---|
| r1 | 6 | 0 | 0% |
| r5 | 9 | 2 | 22% |
| r9 | 14 | 6 | 43% |
Verdicts: holding (rate flat, near zero), drifting (rate
climbing), gone (violations in the majority). End with the response
where drift started and the worst sentence in the session.
Hard Rules
- Report only. Never rewrite the audited text.
- Every violation quotes the text verbatim. No receipt, no row.
- Rule numbers cite Issue 9. Unsure means say unsure; never invent a rule
number.
- Never bundle, quote at length, or reconstruct the STE dictionary.
- Code, commands, error strings, quotes: always exempt.
1---2name: ste-audit3description: Check output against the machine-checkable ASD-STE100 rules: sentence length caps, noun cluster limits, allowed verb forms, -ing restrictions, passive voice, paragraph limits. Use after adding an STE memory line, CLAUDE.md rule, or writer skill, or when replies drift wordy again. Violations table with Issue 9 rule numbers and quoted receipts, plus a drift verdict (holding, drifting, gone). Reports only; never rewrites; no dictionary bundled.4---56# STE Audit78Audit text against ASD-STE100 (Issue 9, January 2025). A memory line or9writer skill sets the style; this verifies it, with rule numbers and10quotes.1112Scope: structural rules only. Dictionary rules (1.2, 1.3: approved words,13approved meanings) need the STE dictionary, which is ASD copyright and not14bundled here. Free copy: request form on asd-ste100.org.1516## Modes1718- Procedural (instructions to act): 20 words max per sentence.19- Descriptive (everything else): 25 words max per sentence.20- Ambiguous sentence: judge at 25 and mark it in the row.2122## Method23241. Collect the assistant's responses in order, or a file the user names.25 Exempt from all checks: code blocks, commands, file paths, URLs, quoted26 error text.272. Split into sentences and paragraphs. Words are whitespace tokens; a28 hyphenated word counts as one.293. Check each sentence against the table.304. Report every violation: verbatim quote + rule number.315. Trend violations per response, first to last.326. Verdict, drift start point, worst sentence.3334## Checks3536| rule | violation to flag |37|---|---|38| 5.1 | procedural sentence over 20 words |39| 6.3 | descriptive sentence over 25 words |40| 6.6 | paragraph with more than six sentences |41| 6.5 | paragraph covering more than one topic (judgment call: name both topics) |42| 2.1 | multi-word noun (noun cluster) longer than three words |43| 3.2 | verb form outside: infinitive, imperative, simple present, simple past, simple future, past participle as adjective |44| 3.4 | stacked auxiliary constructions ("would have been configured") |45| 3.5 | an -ing verb used outside a technical-noun role |46| 3.6 | passive voice where the agent is known |4748## Report4950```markdown51| where | quote | rule | violation |52|---|---|---|---|53| r4 s2 | "the config that was being generated by the daemon" | 3.6 | passive, agent known |54| r7 s1 | 31 words | 6.3 | descriptive cap is 25 |55| r7 s4 | "long running background task execution queue" | 2.1 | five-word noun cluster |56| r9 s3 | "consider leveraging incremental checkpointing" | 3.5 | -ing verb, not a technical noun |57```5859```markdown60| response | sentences | violations | rate |61|---|---|---|---|62| r1 | 6 | 0 | 0% |63| r5 | 9 | 2 | 22% |64| r9 | 14 | 6 | 43% |65```6667Verdicts: **holding** (rate flat, near zero), **drifting** (rate68climbing), **gone** (violations in the majority). End with the response69where drift started and the worst sentence in the session.7071## Hard Rules7273- Report only. Never rewrite the audited text.74- Every violation quotes the text verbatim. No receipt, no row.75- Rule numbers cite Issue 9. Unsure means say unsure; never invent a rule76 number.77- Never bundle, quote at length, or reconstruct the STE dictionary.78- Code, commands, error strings, quotes: always exempt.
brenbuilds1