Skip to content

Commit df90a22

Browse files
committed
docs: fix anti-pattern naming for spec compliance
Rename anti-patterns to use proper Negative + Noun format per pattern-spec.md: - "Constraint Overload" → "Over-Constrained" - "Secret Leakage" → "Leaked Secrets" - "Proving Impossibility" → "Unfounded Impossibility" - "Isolated Prompting" → "Disconnected Prompting" - "Overlapping Workspaces" → "Conflicting Workspaces" Updates README.md, experiments/README.md, examples, migration guide, and rename scripts for consistency.
1 parent 72251ee commit df90a22

5 files changed

Lines changed: 12 additions & 12 deletions

File tree

PATTERN_MIGRATION_GUIDE.md

Lines changed: 3 additions & 3 deletions
Original file line numberDiff line numberDiff line change
@@ -66,9 +66,9 @@ This change aligns with established pattern naming conventions:
6666
| Rushing Into AI | Premature Adoption | Added negative prefix | "Premature" clearly indicates timing failure |
6767
| Context Drift | Broken Context | Added negative prefix | "Broken" indicates failure state |
6868
| Unrestricted Access | Unrestricted Access | No change | Already compliant |
69-
| Shared Agent Workspaces | Overlapping Workspaces | Changed to negative implication | "Overlapping" suggests conflict |
69+
| Shared Agent Workspaces | Conflicting Workspaces | Changed to negative implication | "Conflicting" clearly indicates problem |
7070
| Ad-Hoc AI Development | Unplanned Development | Added negative prefix | "Unplanned" clearly negative |
71-
| Prompt-Only AI Development | Isolated Prompting | Simplified, negative implication | "Isolated" suggests insufficient approach |
71+
| Prompt-Only AI Development | Disconnected Prompting | Simplified, negative implication | "Disconnected" clearly indicates isolation from tools |
7272
| Vague Issue Generation | Under-Specified Issues | Added negative prefix | "Under-Specified" indicates insufficiency |
7373
| Missing CI Integration | Broken Integration | Added negative prefix | "Broken" indicates failure |
7474
| Implementation-First AI | Spec-Ignored | Symmetrical with "Spec-First" | Opposite of the pattern |
@@ -80,7 +80,7 @@ This change aligns with established pattern naming conventions:
8080
| Knowledge Hoarding | Over-Documentation | Changed to "Over-" prefix | More technical description |
8181
| Context Bloat | Bloated Context | Adjusted word order | "Bloated" is negative adjective |
8282
| Unconstrained Generation | Unconstrained Generation | No change | Already compliant |
83-
| Constraint Overload | Constraint Overload | No change | Already compliant |
83+
| Constraint Overload | Over-Constrained | Changed to negative prefix | "Over-" prefix indicates excess |
8484
| Pseudo-Atomic Tasks | False Atomicity | Changed to "False" | More precise negative indicator |
8585
| Over-Decomposition | Over-Decomposition | No change | Already compliant |
8686
| Black Box Development | Blind Development | Changed "Black Box" to "Blind" | Simpler, maintains meaning |

README.md

Lines changed: 3 additions & 3 deletions
Original file line numberDiff line numberDiff line change
@@ -458,7 +458,7 @@ Modern AI development platforms provide enterprise-grade implementations of thes
458458
**Anti-pattern: Unrestricted Access**
459459
Allowing AI tools full system access risks credential leaks, data breaches, and security compliance violations.
460460

461-
**Anti-pattern: Overlapping Workspaces**
461+
**Anti-pattern: Conflicting Workspaces**
462462
Allowing multiple parallel agents to write to the same directories creates race conditions, file conflicts, and unpredictable behavior that can corrupt the development environment.
463463

464464
---
@@ -622,7 +622,7 @@ See [examples/tool-integration/](examples/tool-integration/) for:
622622
- Usage patterns and deployment guidelines
623623
- Integration with [Security Sandbox](#security-sandbox)
624624

625-
**Anti-pattern: Isolated Prompting**
625+
**Anti-pattern: Disconnected Prompting**
626626
Attempting to solve complex data analysis, system integration, or real-time problems using only natural language prompts without providing AI access to actual data sources, APIs, or system tools. This leads to hallucinated responses, outdated information, and inability to interact with real systems.
627627

628628
---
@@ -1372,7 +1372,7 @@ Good: "Reduce p99 latency to <50ms without new dependencies"
13721372
**Anti-pattern: Unconstrained Generation**
13731373
Giving AI vague instructions like "make it better" or "add features" leads to over-engineered solutions that are hard to maintain and review.
13741374

1375-
**Anti-pattern: Constraint Overload**
1375+
**Anti-pattern: Over-Constrained**
13761376
Adding too many constraints ("use exactly 50 lines, 2 methods, no dependencies, 100% test coverage, sub-10ms response time") paralyzes AI decision-making and produces suboptimal solutions.
13771377

13781378
---

experiments/README.md

Lines changed: 2 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -1451,15 +1451,15 @@ Simon's approach:
14511451
- Mark repo as `noindex` for search engines
14521452
- *"I still like to keep AI-generated content out of search, to avoid contributing more to the dead internet."*
14531453

1454-
#### Anti-pattern: Secret Leakage
1454+
#### Anti-pattern: Leaked Secrets
14551455

14561456
**Problem**: Running unrestricted agents on production repos containing credentials.
14571457

14581458
Simon warns: *"A prompt injection attack of the lethal trifecta variety could easily be used to steal sensitive code or environment variables."*
14591459

14601460
**Solution**: Only use unrestricted access on dedicated, secret-free research repos.
14611461

1462-
#### Anti-pattern: Proving Impossibility
1462+
#### Anti-pattern: Unfounded Impossibility
14631463

14641464
**Problem**: Expecting agents to prove something can't be done.
14651465

experiments/examples/asynchronous-research/README.md

Lines changed: 2 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -373,13 +373,13 @@ python automation/result-parser.py research-folder/
373373

374374
**Solution**: Keep research in dedicated repo, mark as `noindex`.
375375

376-
### Secret Leakage
376+
### Leaked Secrets
377377

378378
**Problem**: Running unrestricted agents on repos with production secrets.
379379

380380
**Solution**: Only use unrestricted access on dedicated, secret-free research repos.
381381

382-
### Proving Impossibility
382+
### Unfounded Impossibility
383383

384384
**Problem**: Expecting agents to prove something can't be done.
385385

scripts/apply-pattern-renames.sh

Lines changed: 2 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -98,9 +98,9 @@ apply_renames() {
9898
# Antipattern Renames
9999
sed -i 's/\*\*Anti-pattern: Rushing Into AI\*\*/\*\*Anti-pattern: Premature Adoption\*\*/g' "$file"
100100
sed -i 's/\*\*Anti-pattern: Context Drift\*\*/\*\*Anti-pattern: Broken Context\*\*/g' "$file"
101-
sed -i 's/\*\*Anti-pattern: Shared Agent Workspaces\*\*/\*\*Anti-pattern: Overlapping Workspaces\*\*/g' "$file"
101+
sed -i 's/\*\*Anti-pattern: Shared Agent Workspaces\*\*/\*\*Anti-pattern: Conflicting Workspaces\*\*/g' "$file"
102102
sed -i 's/\*\*Anti-pattern: Ad-Hoc AI Development\*\*/\*\*Anti-pattern: Unplanned Development\*\*/g' "$file"
103-
sed -i 's/\*\*Anti-pattern: Prompt-Only AI Development\*\*/\*\*Anti-pattern: Isolated Prompting\*\*/g' "$file"
103+
sed -i 's/\*\*Anti-pattern: Prompt-Only AI Development\*\*/\*\*Anti-pattern: Disconnected Prompting\*\*/g' "$file"
104104
sed -i 's/\*\*Anti-pattern: Vague Issue Generation\*\*/\*\*Anti-pattern: Under-Specified Issues\*\*/g' "$file"
105105
sed -i 's/\*\*Anti-pattern: Missing CI Integration\*\*/\*\*Anti-pattern: Broken Integration\*\*/g' "$file"
106106
sed -i 's/\*\*Anti-pattern: Implementation-First AI\*\*/\*\*Anti-pattern: Spec-Ignored\*\*/g' "$file"

0 commit comments

Comments
 (0)