pegrex-twin
Query the codebase twin (call graph, ownership, guards, cognitive complexity) and the org twin (teams x compliance x complexity).
Skill by ovoxnox
Chalk Labs
Need help deploying pegrex-twin?
Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/ovoxnox-pegrex-twin
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: security
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/pegrex-twin
What's inside
- Skill name
pegrex-twin- Description
- Query the codebase twin (call graph, ownership, guards, cognitive complexity) and the org twin (teams x compliance x complexity). Use for "which functions/teams are at risk?" questions.
- License
- MIT
- Instructions
- 9 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
# digital twins - `twin.ask(twin, "which functions can reach db_execute?")` answers with guards attached. Unknown question shapes refuse loudly. - `twin.cognitive_report(twin, budget=N)` + `orgtwin.org_report(root)`: "which team misses SOC2 and is over budget?" is one join. Teams with no data are UNKNOWN, never clean. ## Repository evidence and operational traces - `build_repository_twin` joins calls, ownership, contracts, dependencies, supplied change history, and declared exposures under a content identity. `twin_function_risk` separates function impact from module dependency impact. - `detect_architecture_drift` reports unintended imports and internal calls; incomplete repository evidence stays UNKNOWN. - `replay_incident` maps runtime events to feasible/unknown/infeasible contract paths and evaluates patch candidates without applying them. - `prioritize_symbolic_paths` retains and prioritizes unseen feasible paths. Traces do not prove unseen paths impossible; path-cap results have no partial ranking. - `simulate_change_impact` evaluates proposed changes only in staging and reports potentially invalidated contracts, policies, generated clients, flows, and downstream modules. It never applies the patch or authorizes a merge.
From ovoxnox/pegrex, MIT.
More from ovoxnox/pegrex
- 0.565score
pegrex-agents
ovoxnox
Integrate pegrex with AI agents via its three protocols (JSON-lines service, ACP, MCP with router).
SkillAFreshness: AClaude Code +9 - 0.565score
pegrex-audit
ovoxnox
Audit source files for security issues with the pegrex engine (patterns + taint + SCA).
SkillAFreshness: AClaude Code +9 - 0.565score
pegrex-coverage
ovoxnox
Turn coverage data into constraint-aware gap analysis and synthesized tests.
SkillAFreshness: AClaude Code +9 - 0.565score
pegrex-specs
ovoxnox
Generate AI-consumable spec schemas (multi-view analysis with prioritized, machine-checkable tasks).
SkillAFreshness: AClaude Code +9 - 0.565score
pegrex-translate
ovoxnox
Verify cross-language translations and refactors with certificates.
SkillAFreshness: AClaude Code +9 - 0.559score
pegrex-verify
ovoxnox
Prove patches and diffs correct with verify_patch, semantic_diff, and the CEGIS repair loop.
SkillAFreshness: AClaude Code +9 - 0.556score
pegrex-safety
ovoxnox
Constrain coding-agent actions with verified policies.
SkillAFreshness: AClaude Code +9 - 0.556score
pegrex-ml
ovoxnox
Verify ML graph equivalence after quantization or pruning with interval bounds plus concrete simulation.
SkillAFreshness: AClaude Code +9 - 0.556score
pegrex-concolic
ovoxnox
Run code concretely, collect branch traces, and flip branches by solving path constraints.
SkillAFreshness: AClaude Code +9 - 0.556score
pegrex-infra
ovoxnox
Verify infrastructure-as-code (Zelkova-style IAM evaluation, Terraform findings) and sign provenance (SLSA-style attestations).
SkillAFreshness: AClaude Code +9 - 0.556score
pegrex-legacy
ovoxnox
Modernize COBOL and Fortran to certified Python (or back).
SkillAFreshness: AClaude Code +9 - 0.553score
pegrex-compliance
ovoxnox
GDPR data-flow findings, SOC2 control presence, legal-deadline CI artifacts.
SkillAFreshness: AClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Oct 24, 2026 (7 days ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/ovoxnox/pegrex
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from ovoxnox
- 0.565score
pegrex-agents
ovoxnox
Integrate pegrex with AI agents via its three protocols (JSON-lines service, ACP, MCP with router).
SkillAFreshness: AClaude Code +9 - 0.565score
pegrex-audit
ovoxnox
Audit source files for security issues with the pegrex engine (patterns + taint + SCA).
SkillAFreshness: AClaude Code +9 - 0.565score
pegrex-coverage
ovoxnox
Turn coverage data into constraint-aware gap analysis and synthesized tests.
SkillAFreshness: AClaude Code +9 - 0.565score
pegrex-specs
ovoxnox
Generate AI-consumable spec schemas (multi-view analysis with prioritized, machine-checkable tasks).
SkillAFreshness: AClaude Code +9 - 0.565score
pegrex-translate
ovoxnox
Verify cross-language translations and refactors with certificates.
SkillAFreshness: AClaude Code +9 - 0.559score
pegrex-verify
ovoxnox
Prove patches and diffs correct with verify_patch, semantic_diff, and the CEGIS repair loop.
SkillAFreshness: AClaude Code +9
Done for you
Rather not set it up yourself?
Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.
See how we build AI agents →Read the case studies
Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.
- launches shipped
- 50+
- launches shipped
- media placements
- 500+
- media placements
- founders on every account
- 2
- founders on every account
Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block
Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.
Get pegrex-twin running in your business
Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.
Cite this page
pegrex-twin skill. Agent Mart. https://agentmart.dev/skills/ovoxnox-pegrex-twin (last updated 2026-10-24)