ruflo-ai-team
claudeTenant-isolated AI teams that plan work, coordinate tasks, recall approved context, and return evidence-backed results
6 skills · 6 commands · 4 agents · 1 MCP server
Chain-of-custody evidence handling — hash, timestamp, inspect metadata, append to an immutable custody register, package as BagIt, verify, and sync to WORM or S3 Object Lock storage.
Not in a marketplace yet, so it loads for one session with --plugin-dir.
Plugin evidence-ops in shotcowboystyle/evidence-ops-plugin. Commands read from the repo's manifest — 1 month ago.
bag-evidenceUse when a set of items must be handed over or archived as one unit — packages a directory as a BagIt bag with per-file checksums and a manifest that any receiving party can validate without this plugin. Triggers - "bag this evidence", "package for handover", "make a BagIt archive".
capture-webUse when a web page needs to be preserved as evidence — archives it as a single self-contained file, records the capture context that the page itself cannot prove, hashes the result, and offers to register it. Triggers - "archive this URL", "capture a webpage as evidence", "save this page before it
environment-checkUse when the user wants to know which evidence-handling tools are present on this host before running a pipeline — probes hashing, metadata, timestamping, packaging, and storage CLIs and reports what is missing with an install hint for each. Triggers - "check evidence tools", "what forensics tools a
hash-evidenceUse when a file or directory needs cryptographic hashes — computes SHA-256 by default and optionally BLAKE3, emitting a checkable manifest for directories. Triggers - "hash this file", "sha256 a folder", "make a checksum manifest".
init-evidence-storeUse when starting a new evidence collection or adding custody handling to an existing workspace — creates the evidence directory tree, an empty append-only register, and a written record of the hashing policy in force. Triggers - "start an evidence store", "set up chain of custody here", "create the
inspect-metadataUse when the embedded metadata of a file matters — extracts EXIF, IPTC, XMP, and container metadata to JSON, then flags anomalies such as timestamp disagreement or editing-software markers as signals worth investigating. Triggers - "read the EXIF on this", "does this photo have GPS", "check this vid
install-depsUse after environment-check reports missing tools — installs them, putting Python-based tools in a plugin-owned virtual environment instead of mutating the system Python. Triggers - "install evidence tools", "set up exiftool and ots", "fix missing forensics dependencies".
log-custodyUse when an item must enter the custody record — hashes it, captures who handed it over and how, copies the original into immutable storage under its own name, and appends one record to the append-only register. Triggers - "log this evidence", "add to the custody register", "record chain of custody
onboardUse on first run or on a new machine — checks the environment, offers to install what is missing, configures a storage destination, and ends by showing the shortest working pipeline for this host. Triggers - "set up evidence-ops", "first run", "get me started with evidence handling".
reference-lookupUse when deciding how to handle a media type, storage mode, or integrity question — searches this plugin's own reference corpus and returns the most relevant passages with their file paths. Triggers - "how do I redact video", "what is object lock compliance mode", "which hash tool on macOS".
setup-storageUse when configuring where evidence is replicated — walks through defining a storage remote, confirms its retention or write-once behaviour, and records the destination policy without ever touching credentials. Triggers - "set up evidence storage", "configure the rclone remote", "where should eviden
sync-immutableUse when verified evidence should be replicated to storage that cannot silently rewrite it — copies to the configured remote, confirms retention settings before writing, and re-verifies what landed. Triggers - "push evidence to immutable storage", "sync to object lock", "back up the evidence bundle"
timestamp-evidenceUse when a file's existence at a point in time needs to be provable independently of the filesystem — anchors its hash with OpenTimestamps and stores the proof alongside the custody record. Triggers - "timestamp this evidence", "prove this existed today", "opentimestamps this file".
verify-bundleUse when integrity must be confirmed rather than assumed — recomputes every hash, validates bags and timestamp proofs, and reports an explicit pass or fail naming each diverging file. Triggers - "verify this evidence", "has anything changed", "check the bag is still valid".
/evidence-ops:bagPackage a directory as a BagIt bag with per-file checksums and a validatable manifest.
/evidence-ops:captureArchive a URL as a self-contained file, hash it, and record the capture context.
/evidence-ops:checkProbe this host for evidence-handling CLIs and report what is present, missing, and how to install it.
/evidence-ops:hashCompute SHA-256 (and optionally BLAKE3) for a file or directory and write a checkable manifest.
/evidence-ops:initCreate the evidence directory tree and an empty append-only custody register in the current workspace.
/evidence-ops:logHash an item, capture its custody metadata, and append one record to the append-only evidence register.
/evidence-ops:lookupSearch this plugin's reference corpus and return the most relevant passages with their paths.
/evidence-ops:metadataExtract EXIF, IPTC, XMP, and container metadata to JSON and flag anomalies worth investigating.
/evidence-ops:onboardFirst-run setup — environment check, dependency install, and storage configuration.
/evidence-ops:syncReplicate verified evidence to immutable storage and re-verify what landed.
/evidence-ops:timestampAnchor a file's hash with OpenTimestamps, or upgrade and verify an existing proof.
/evidence-ops:verifyRecompute hashes, validate bags and timestamp proofs, and report an explicit pass or fail.
Tenant-isolated AI teams that plan work, coordinate tasks, recall approved context, and return evidence-backed results
6 skills · 6 commands · 4 agents · 1 MCP server
Cedar policy enforcement + Ed25519 signed receipts for every Claude Code tool call. First cryptographic governance plugin — decisions are policy-gated before they run and every decision produces a tamper-evident receipt verifiable offline.
1 skill · 2 commands · 2 agents · hooks
818 cybersecurity skills covering web security, pentesting, DFIR, threat intelligence, cloud security, malware analysis, and more. Mapped to 6 frameworks.
200 skills
Evidence-backed BioPharma research workflows over Maven Bio's drug, trial, company, and deal knowledge graph. Skills for competitive pipelines, indication landscapes, asset profiles, deal and financing activity, and evidence synthesis grounded in FDA, SEC, clinical, and press sources. Requires a Maven Bio account.
16 skills · 1 agent · 1 MCP server
45 advanced engineering skills: agent designer, agent workflow designer, RAG architect, database designer + schema designer + SQL assistant, migration architect, observability designer, dependency auditor, changelog generator, API design reviewer, API test suite builder, CI/CD pipeline builder, MCP server builder, skill security auditor, skill tester, performance profiler, focused-fix, browser-automation, full-page-screenshot, git-worktree-manager, monorepo-navigator, codebase-onboarding, interview-system-designer, runbook-generator, spec-driven-workflow, secrets-vault-manager, env-secrets-manager, pr-review-expert, self-eval, tc-tracker, feature-flags-architect, kubernetes-operator, chaos-engineering, ship-gate, slo-architect (error-budget + multi-window burn-rate alerts per Google SRE Workbook), tech-debt-tracker, agent-regression-evals, coding-agent-rollout, commit-craft, agent-run-forensics and i18n-localization. Agent skill and plugin for Claude Code, Codex, Gemini CLI, Cursor, OpenClaw.
48 skills · hooks
PUA productivity coaching — modular skills, 15 workplace/corporate flavors including Ding Inside/Outside, completion-quality checks, retry/change-approach reminders, and feedback tools.
29 skills · 22 commands · 7 agents · hooks
This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.