astra-review
Skill1 starsChanged 21 days agoMITView on GitHub
Codex CLI review configured for gpt-6-astra at medium reasoning. Same verified CLI lifecycle as codex-review. Use for $astra-review or 'have Astra review this'.
We split this skill into the rules it gives an agent
2 rules. About 0 are common, 2 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈2
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 8
Follow the complete execution contract of the native codex-review skill: current local preflight, exact scope, unique run directory, source …
- Distinctive: line 33
Commit and uncommitted prompts, the root-commit and dirty-tree rules, the skill-load and scope-identity checks, prompt escaping, and path …
≈ “Common” is an estimate: at least 1 in 5 of the 308,232 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Astra review
Follow the complete execution contract of the native codex-review skill: current local preflight, exact scope, unique run directory, source manifest, launch path (external-review first, selector fallback), process completion, report identity, finding verification, and honest attribution. This entrypoint changes only the defaults:
| Setting | Astra default |
| Model | gpt-6-astra |
| Effort | medium, regardless of diff size |
| Run directory prefix | .tmp/astra-review- |
Invoked from Codex, the reviewer shares the author's vendor: it supplies fresh context, not vendor independence. Say so in the result.
Skip the newest-Sol check in codex-review Step 1; this entrypoint never swaps Astra for Sol. Honor an explicit user model or effort choice. Confirm supported local options before inference; a model identifier in this file is not proof of availability. The invocation input carries scope as in codex-review.
Example for a branch diff after creating a fresh $RUN directory (POSIX shell):
mkdir -p .tmp
RUN=$(mktemp -d .tmp/astra-review-XXXXXXXX)
git fetch origin main
BASE=$(git merge-base origin/main HEAD); HEAD_SHA=$(git rev-parse HEAD)
# External-review path (.agents/skills/external-review/SKILL.md exists):
codex exec review "Read .agents/skills/external-review/SKILL.md completely and follow it for this review of the branch diff: base $BASE, head $HEAD_SHA. Read the diff with git diff $BASE $HEAD_SHA. Leaf review: no agents, no nested reviews, no edits." -m gpt-6-astra -c model_reasoning_effort=medium -o "$RUN/report.md" < /dev/null > "$RUN/run.log" 2>&1
# Selector path (no external-review skill):
codex exec review --base origin/main -m gpt-6-astra -c model_reasoning_effort=medium -o "$RUN/report.md" < /dev/null > "$RUN/run.log" 2>&1Commit and uncommitted prompts, the root-commit and dirty-tree rules, the skill-load and scope-identity checks, prompt escaping, and path attribution follow codex-review.
On PowerShell, use a GUID-named directory and supported stdin and output redirection as described in codex-review. Distinct prefixes do not prevent collisions between two Astra invocations; every run must still be unique.
If Astra is unavailable, report that outcome. Do not silently inherit another model or attribute a fallback to Astra. A rejected Astra id is reported, never retried on another model; any other failure gets the one automatic retry from codex-review. A retry uses a new directory and reports its observed model and effort, or explicitly marks model resolution unverified. Keep lifecycle fixes in codex-review rather than forking them here.
The requested review does not authorize fixes, commits, pushes, PRs, merges, publication, machine configuration changes, or paid credit purchases.
Other versions5 projects use a version of this.
Word for word · 4
- ryanportfolio/Corewise.Academy★ 1100% same
- ryanportfolio/savetokens★ 1100% same
- ryanportfolio/STK★ 1100% same
- ryanportfolio/HarnessFirmware.com★ 0100% same
Edited · 0
None found.
Wrote their own version · 1
- howells/skills★ 4same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
Used alongsideProjects with it also use compact-review.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
ryanportfolioSkillcompact-review
Use on /compact-review or right before /compact: review the session and return copy-ready custom instructions for /compact that keep what matters. Does not run /compact.
Also in 4 projects that use this
In this repository85 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- addskillSkill
- adopt-repoSkill
- advocateSkill
- apply-firmwareSkill
- arenaSkill
- babysit-ciSkill
- brainstormingSkill
- broSkill
- cache-loopSkill
- cavemanSkill
- claude-reviewSkill
- codex-reviewSkill
- dareSkill
- deep-planSkill
- design-prototypesSkill
- enhance-promptSkill
- external-reviewSkill
- fable-modeSkill
- forge-repo-ui-skillSkill
- handoff-auditSkill
- impartial-reviewSkill
- init-projectSkill
- labSkill
- long-horizonSkill
- optimize-contextSkill
- opus-fullreviewSkill
- perf-loopSkill
- recallSkill
- redesign-conceptsSkill
- refineSkill
- serversSkill
- session-hubSkill
- showpieceSkill
- sync-starterSkill
- whySkill
- wow-loopSkill
- wrapupSkill
- writing-plansSkill
- writingSkill
- addskillSkill
- adopt-repoSkill
- advocateSkill
- apply-firmwareSkill
- arenaSkill
- astra-fullreviewSkill
- astra-reviewSkill
- babysit-ciSkill
- brainstormingSkill
- broSkill
- cache-loopSkill
- cavemanSkill
- claude-reviewSkill
- codex-fullreviewSkill
- codex-image-genSkill
- codex-reviewSkill
- coordinateSkill
- dareSkill
- deep-planSkill
- The first 60 shown.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
Reviews can't be read right now.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

