avmnu-sng

avmnu-sng/sutra

Plugin Claude Code

Sutra -- a plug-and-play agent kit for Claude Code: senior-engineer methodologies, skills, subagents, and layered operating profiles.

avmnu-sng/sutra

Plugin Claude Code

A senior-engineer operating system for Claude Code -- architecture review, verification discipline, multi-session build orchestration, doc sanitization, and commit craft, delivered as skills, subagents, and layered lite/standard/strict profiles.

avmnu-sng/sutra

Agent

Dispatch to run a rigorous 7-point architecture review of a named service or component -- it reads the code and infra manifests, traces at least one real request path per distinct request type, stress-tests the design at 2x/5x/10x with explicit math, and returns severity-ranked findings, each with a quantified…

avmnu-sng/sutra

Agent

Dispatch to verify ONE specific factual claim about the code against the actual source -- e.g. "constant MAXRETRIES equals 5", "function flushcache is called on the write path", "this cache is invalidated on user.updated". Returns CONFIRMED or REFUTED with exact file:line evidence. Use it whenever a decision depends…

avmnu-sng/sutra

Agent

Dispatch before publishing code or docs (open-sourcing, a public sample, sharing externally) to scan them for private material that must not ship -- secrets and credentials, and internal identifiers (paths, usernames, hosts, IPs, internal URLs, employer/product/service names, emails, account IDs) -- against a…

avmnu-sng/sutra

Agent

Dispatch when you need an exact, code-grounded trace of one request/message/event as it flows end to end through the codebase -- entry point through every call, I/O, branch, lock/retry, error path, and final side effect. Use it to answer "what actually happens when X comes in?" not to get advice or a refactor.

avmnu-sng/sutra

Hook

Runs when a session starts on startup, resume, clear and compact, executing inject-profile.sh. From avmnu-sng/sutra.

avmnu-sng/sutra

Hook

Runs after a tool call finishes for Write and Edit tool calls, executing ascii-guard.sh. From avmnu-sng/sutra.

avmnu-sng/sutra

Skill Claude CodeCodex

Use when structuring or auditing a repo's agent-facing documentation -- entry docs, a shared rulebook, routing and handoff tables, skill ordering, and a source-of-truth designation -- so agents and humans navigate it reliably.

avmnu-sng/sutra

Skill Claude CodeCodex

Use when deciding whether to delegate work to subagents and how to prompt, verify, and integrate their output; covers what agents do well and what they systematically miss.

avmnu-sng/sutra

Skill Claude CodeCodex

Use when reviewing a backend or service architecture for scalability, resource fit, and cost -- trace requests, stress each component, model 2x/5x/10x load, and produce ROI-quantified recommendations.

avmnu-sng/sutra

Skill Claude CodeCodex

Use when auditing an existing codebase and sequencing fixes -- produce a structured audit doc, prioritize findings across three lenses, and split remediation work so humans and agents can proceed in parallel; not for greenfield planning.

avmnu-sng/sutra

Skill Claude CodeCodex

Use when writing or revising a git commit message, splitting work into commits, or structuring a branch so a future engineer running git blame understands the change.

avmnu-sng/sutra

Skill Claude CodeCodex

Use when changing a live schema or moving data in a running system -- apply expand/contract (parallel change) so old and new shapes coexist, backfill in resumable batches, verify integrity, and switch reads only after the new shape is proven.

avmnu-sng/sutra

Skill Claude CodeCodex

Use when isolating a defect or root-causing a failure -- contain a live incident first, then reproduce, instrument, form one falsifiable hypothesis at a time, bisect, and prove the mechanism before calling it fixed.

avmnu-sng/sutra

Skill Claude CodeCodex

Use when deciding how much energy -- tokens, agent fan-out, verification passes, independent attempts, artifacts -- a task is worth, so spend tracks complexity times blast radius without ever trading away the correctness floor.

avmnu-sng/sutra

Skill Claude CodeCodex

Use when authoring a Claude Code hook -- writing a PreToolUse/PostToolUse/SessionStart/UserPromptSubmit checker -- to get the fail-open guard skeleton and advisory-vs-blocking recipes so a hook reports without ever breaking the user's flow.

avmnu-sng/sutra

Skill Claude CodeCodex

Use when planning or running a large build that spans many sessions or agents, to add gates that keep the assembled, deployed system honest -- not just each component -- and to prove "done" instead of assuming it.

avmnu-sng/sutra

Skill Claude CodeCodex

Use when running multiple agents or sessions concurrently against shared state, to pick an isolation regime and coordination protocol that stops two writers from corrupting the same file, branch, or working tree.

avmnu-sng/sutra

Skill Claude CodeCodex

Use when optimizing runtime performance -- establish a baseline, profile the actual hot path, validate the win on a macro scenario, and lock it in with a regression guard.

avmnu-sng/sutra

Skill Claude CodeCodex

Use at the end of a work session, or whenever recording a durable lesson -- run a probe-backed retro, reconcile outside critique, and capture only the lessons that survive.

avmnu-sng/sutra

Skill Claude CodeCodex

Scaffold a repeatable execution-plan structure and wire in the build-orchestrator workflow when starting a large, multi-session build that must survive across many sessions.

avmnu-sng/sutra

Skill Claude CodeCodex

Use before open-sourcing or otherwise publishing your own code or docs -- remove secrets, credentials, and internal identifiers, and verify the scrub with a repeated search, so nothing private ships.

avmnu-sng/sutra

Skill Claude CodeCodex

Use when adding or upgrading a dependency, reviewing a lockfile diff, handling a security advisory, provisioning tokens or secrets, or vetting supply-chain risk -- the standing-liability angles that a diff-level vuln scan does not cover.