TDvorak/Devour
1
0
Fork 0
mirror of https://github.com/Dvorinka/Devour.git synced 2026-06-03 20:13:03 +00:00
Code Issues Packages Projects Releases Wiki Activity

i dont like commits

Browse Source
This commit is contained in:
Tomas Dvorak
2026-02-24 12:10:13 +01:00
parent 898a3c303f
commit 1d72a1cc01
109 changed files with 43586 additions and 8484 deletions
Download Patch File Download Diff File Expand all files Collapse all files
AGENTS.md
+69 -21
View File
@@ -8,11 +8,14 @@ description: >
duplicate functions, code smells, naming issues, import cycles, or coupling
problems. Also use when asked for a health score, what to fix next, or to
create a cleanup plan. Supports 28 languages.
allowed-tools: Bash(desloppify *)
allowed-tools: Bash(devour quality*, devour review*, devour scorecard*)
---
# Desloppify
Devour delegates quality/review operations to `desloppify`.
Use Devour entrypoints (`devour quality ...`, `devour review ...`, `devour scorecard`) so users stay in one CLI surface.
## 1. Your Job
**Improve code quality by fixing findings and maximizing strict score honestly.**
@@ -33,11 +36,11 @@ Never skip scores. The user tracks progress through them.
scan → follow the tool's strategy → fix or wontfix → rescan
```
1. `desloppify scan --path .` — the scan output ends with **INSTRUCTIONS FOR AGENTS**. Follow them. Don't substitute your own analysis.
1. `devour quality scan --path .` — this delegates to `desloppify scan`; follow the output **INSTRUCTIONS FOR AGENTS** exactly.
2. Fix the issue the tool recommends.
3. `desloppify resolve fixed "<id>"` — or if it's intentional/acceptable:
`desloppify resolve wontfix "<id>" --note "reason why"`
4. Rescan to verify.
3. `devour quality resolve fixed "<id>"` — or if it's intentional/acceptable:
`devour quality resolve wontfix "<id>" --note "reason why"`
4. Rescan to verify via `devour quality scan --path .`.
**Wontfix is not free.** It lowers the strict score. The gap between lenient and strict IS wontfix debt. Call it out when:
- Wontfix count is growing — challenge whether past decisions still hold
@@ -47,23 +50,24 @@ scan → follow the tool's strategy → fix or wontfix → rescan
## 3. Commands
```bash
desloppify scan --path src/ # full scan
desloppify scan --path src/ --reset-subjective # reset subjective baseline to 0, then scan
desloppify next --count 5 # top priorities
desloppify show <pattern> # filter by file/detector/ID
desloppify plan # prioritized plan
desloppify fix <fixer> --dry-run # auto-fix (dry-run first!)
desloppify move <src> <dst> --dry-run # move + update imports
desloppify resolve fixed|wontfix|false_positive "<pat>" # classify finding outcome
desloppify review --prepare # generate subjective review data
desloppify review --import file.json # import review results
devour quality scan --path src/ # full scan
devour quality scan --path src/ --reset-subjective # reset subjective baseline to 0, then scan
devour quality next --count 5 # top priorities
devour quality show <pattern> # filter by file/detector/ID
devour quality plan # prioritized plan
devour quality fix <fixer> --dry-run # auto-fix (dry-run first!)
devour quality move <src> <dst> --dry-run # move + update imports
devour quality resolve fixed|wontfix|false_positive "<pat>" # classify finding outcome
devour review --prepare # generate subjective review data
devour review --import file.json # import review results
devour review # default batch run (codex+parallel+scan-after-import)
```
## 4. Subjective Reviews (biggest score lever)
Score = 40% mechanical + 60% subjective. Subjective starts at 0% until reviewed.
1. `desloppify review --prepare` — writes dimension definitions and codebase context
1. `devour review --prepare` — delegates to `desloppify review --prepare` and writes dimension definitions and codebase context
to `query.json`.
2. **Review each dimension independently.** For best results, review dimensions in
@@ -78,7 +82,7 @@ Score = 40% mechanical + 60% subjective. Subjective starts at 0% until reviewed.
3. Merge assessments (average scores if multiple reviewers cover the same dimension)
and findings, then import:
```bash
desloppify review --import findings.json
devour review --import findings.json
```
Required output format per reviewer:
@@ -96,7 +100,7 @@ Score = 40% mechanical + 60% subjective. Subjective starts at 0% until reviewed.
}
```
Need a clean subjective rerun from zero? Run `desloppify scan --path src/ --reset-subjective` before preparing/importing fresh review data.
Need a clean subjective rerun from zero? Run `devour quality scan --path src/ --reset-subjective` before preparing/importing fresh review data.
Even moderate scores (60-80) dramatically improve overall health.
@@ -127,7 +131,51 @@ When desloppify itself appears wrong or inconsistent:
## Prerequisite
`command -v desloppify >/dev/null 2>&1 && echo "desloppify: installed" || echo "NOT INSTALLED — run: pip install --upgrade git+https://github.com/peteromallet/desloppify.git"`
`command -v desloppify >/dev/null 2>&1 && echo "desloppify: installed" || echo "NOT INSTALLED — run: pip install --upgrade \"desloppify[full]\""`
## Install-and-Run Prompt (Copy/Paste)
```text
Install or update desloppify, then scan this codebase for code quality issues
(dead code, duplication, complexity, smells). It tracks findings persistently
across sessions and reports a health score.
Requires Python 3.11+. Install from PyPI:
pip install --upgrade desloppify
# Recommended for deepest coverage (tree-sitter + Python security adapter):
pip install --upgrade "desloppify[full]"
desloppify update-skill codex # pick yours: claude, cursor, codex, copilot, windsurf, gemini
Use Devour wrappers (delegates to desloppify):
devour quality scan --path .
devour quality status
devour quality next
Direct equivalent commands:
desloppify scan --path .
desloppify status
desloppify next
--path is the directory to scan (use "." for the whole project, or "src/" etc).
Language is auto-detected. To override: desloppify --lang python scan --path .
(note: --lang goes BEFORE the subcommand)
Fix what it finds, then:
desloppify resolve fixed <id> --note "what changed" --attest "I have actually [DESCRIBE THE CONCRETE CHANGE YOU MADE] and I am not gaming the score by resolving without fixing."
For false positives:
desloppify resolve wontfix <id> --note "reason" --attest "I have actually verified this is intentional/false-positive and I am not gaming the score by resolving without fixing."
If subjective scores feel stale or inflated:
desloppify scan --path . --reset-subjective
Because state persists, run regularly (for example before each push).
If anything seems wrong/confusing in desloppify itself, capture a repro and ask
whether to log an upstream issue.
If you need to debug desloppify internals:
git clone https://github.com/peteromallet/desloppify.git /tmp/desloppify
```
<!-- desloppify-end -->
@@ -135,7 +183,7 @@ When desloppify itself appears wrong or inconsistent:
This is the canonical Codex overlay used by the README install command.
1. Prefer first-class batch runs: `desloppify review --run-batches --runner codex --parallel`.
1. Prefer first-class batch runs: `devour review` (default) or `devour review --run-batches --runner codex --parallel`.
2. The command writes immutable packet snapshots under `.desloppify/review_packets/holistic_packet_*.json`; use those for reproducible retries.
3. Keep reviewer input scoped to the immutable packet and the source files named in each batch.
4. Do not use prior chat context, score history, narrative summaries, issue labels, or target-threshold anchoring while scoring.
@@ -152,7 +200,7 @@ This is the canonical Codex overlay used by the README install command.
```
7. Keep `findings` schema compatible with `query.system_prompt`.
8. If a batch fails, retry only that slice with `desloppify review --run-batches --packet <packet.json> --only-batches <idxs>`.
8. If a batch fails, retry only that slice with `devour review --run-batches --packet <packet.json> --only-batches <idxs>`.
<!-- desloppify-overlay: codex -->
<!-- desloppify-end -->