96 projects
checksum-claim-audit
Offline auditor for documented checksum-verification promises in Python projects.
logging-claim-audit
Offline auditor for documented record-keeping promises in Python projects.
progress-claim-audit
Offline auditor for documented ongoing-work feedback promises in Python projects.
validation-claim-audit
Offline auditor for documented input-checking promises in Python projects.
batch-claim-audit
Offline auditor for documented grouped-handling promises in Python projects.
compression-claim-audit
Offline auditor for documented size-reduction promises in Python projects.
encryption-claim-audit
Offline audit of documented at-rest protection promises against Python source.
idempotency-claim-audit
Offline audit of documented re-run claims against Python source.
silent-claim-audit
Offline auditing of documented terminal-output claims against Python source.
shutdown-claim-audit
Offline audit of documented interruption promises against Python source.
locking-claim-audit
Offline audit of documented cross-process exclusion promises against Python source.
async-claim-audit
Audit documented awaitability promises against static Python evidence.
thread-safety-claim-audit
Offline audit of documented thread-safety claims against Python source.
interactive-claim-audit
Offline static audit of documented interactivity claims.
recursion-claim-audit
Audit documented directory traversal depth against Python source.
pagination-claim-audit
Offline audit of documented pagination claims against Python source.
agent-guard-hooks
Behavior-guardrail hooks for Claude Code, Codex CLI and Gemini CLI: test-tampering + outbound-action guards, gate-liveness verification, and mutation test-honesty
sort-claim-audit
Offline audit of documented sort-order claims against Python source.
timeout-claim-audit
Offline audit of documented timeout promises against Python source.
cache-claim-audit
Offline-audit of documented cache-reuse promises against Python source.
retry-claim-audit
Offline audit of documented retry claims against Python source.
concurrency-claim-audit
Offline audit of documented concurrency claims against Python source.
atomic-claim-audit
Offline audit of documented atomic-write claims against Python source.
streaming-claim-audit
Offline static audit of documented streaming and low-memory claims
encoding-claim-audit
Offline audit of documented text encoding claims against Python source
zero-config-claim-audit
Offline audit of documented config requirements against Python source
determinism-claim-audit
Offline static audit of documented Python determinism claims
security-claim-audit
Offline static auditing of documented execution-safety promises
auth-claim-audit
Offline audit of documentation credential claims against Python evidence
readonly-claim-audit
Offline static audit of documented read-only claims against Python writes
format-claim-audit
Offline static audit of documented data-format claims in Python projects
platform-claim-audit
Offline static audit of documented Python platform promises
error-claim-audit
Offline audit of documented Python error behaviour
schema-claim-audit
Offline static audit of documented JSON field names against Python code
config-claim-audit
Offline audit of documented Python configuration defaults
entry-claim-audit
Offline static audits of Python entry-point claims
readme-claim-audit
Deterministic offline README claim auditing
api-claim-audit
Offline static audit of documented Python API claims
privacy-claim-audit
Offline static audit of privacy prose against Python source
dep-claim-audit
Offline static audit of Python dependency and compatibility claims
done-claim-audit
Offline heuristic audit of completion claims against transcripts and git
skill-drift
Offline heuristic auditing of skill package claims
instruction-drift
Offline heuristic checks for stale repository instructions
compact-audit
Offline surface matching audit of compaction summaries
startup-trust-guard
Inspect agent startup instructions and configuration trust
swarm-tree
Hierarchical multi-agent orchestration: a tree of LLM agents, each node backed by a different provider
mcp-idprobe
Runtime probe for MCP cross-tenant response leaking via JSON-RPC id collision (CVE-2026-111770)
watchtower-guard
Tamper-evident integrity watcher for an agent's own guardrails: who watches the watchers.
human-gate
Cross-platform human approval channel for coding agents: agents request, humans approve, timeouts default-deny.
fleet-guard
Machine-resource guard layer for fleets of coding-agent sessions: background-process quotas, stall watchdog, leak reaping, disk guard.
apimirage
Catch hallucinated and deprecated API usage: AST scan plus real importlib existence checks
tool-throttle
MCP tool-call throttling: token-bucket rate limits per tool name, a fuse against runaway agents
script-chain-walk
Trace cross-file script call chains: build a dependency graph of shell/Python scripts, find broken chains and call cycles
bash-write-targets
Statically list the file-write targets of a bash command (redirects, tee, -o flags, cp/mv destinations)
contradiction-judge
Semantic contradiction detection for AI memory systems
tagpoint
Verify a PyPI release actually matches its GitHub tag — name AND content
cache-doctor
Semantic-cache health diagnostics: hit rate, expiry, and cache-pollution analysis for LLM response caches
worktree-janitor
Clean up git worktrees left behind by dead agent sessions
mcp-config-dedupe
Detect duplicate, drifted, and dead MCP server configs across clients — and dedupe them in one command
session-archive
Archive Claude Code session logs before the 30-day auto-delete: gzip + searchable index + restore
canarygate
Hook/gate liveness validator: canary probes + synthetic events that catch wired-but-dead gates
vibe-shipcheck
Pre-publish security config check for vibe-coded apps: committed .env files, hardcoded secrets, exposed Supabase URLs, missing RLS, wildcard CORS, debug flags.
routine-sweeper
Unattended cleanup of Claude Code routine (scheduled task) run sessions: batch-prune old runs by policy, with dry-run preview and whitelist protection
blackbox-bill
Explain where your AI-coding-tool money went: billing black-box explainer with tokenizer-aware per-project and subagent cost attribution
css-slop-detector
Score CSS/HTML for AI-generated design cliches — and auto-fix them with --fix
mcp-cve-watch
Continuous CVE intelligence for your MCP servers' runtime dependencies
subagent-budget-team
Team/CI budget control for subagent token spend: shared budget pools, per-agent quotas, overspend checks, and a kill switch.
webmcp-bridge
Expose Browser Buddy's logged-in-browser tools as WebMCP-callable endpoints (stdlib only)
skill-pin-verify
Integrity verifier for AI agent skill packages: pin tarballs by SHA-256 and scan for install hooks, exfiltration, and obfuscation.
contextleak
Check which sensitive files your Docker build context would leak into the image
phantom-deps
Hallucinated-dependency scanner: verify every package in your manifests and imports actually exists on PyPI/npm before you install
pin-deep
Recursive GitHub Actions pin checker: flag unpinned nested uses hiding behind your SHA-pinned actions
skill-tax-cli
Audit the context tax of your Claude Code skills; detect silent listing-budget drops; CI gate
decision-log
Append-only decision log for coding-agent sessions, with read-time verification and a write-time gate
resume-budget-guard
Enforce a cumulative spend cap across Claude Code resumes, with quota-aware auto-wake
rules-doctor
Health-check your CLAUDE.md / AGENTS.md rule files: dead @imports, shadowed files, instruction bloat.
subagent-tax
Estimate how much of your Claude Code bill is subagent preamble resends
readmeta
Check that your README will actually render on PyPI — inspects the built artifact, not the repo
session-handover
Hand off a coding-agent session to the next one: reads Claude Code and Codex CLI transcripts, generates a handover doc
frontmatter-guard
Semantic linter for Claude Code skill/plugin frontmatter — catches silent key typos official validators miss
deny-probe
Penetration tester for Claude Code permission deny rules
memgovern
Memory governance for AI agents: decay, tombstones, conflict arbitration, audit
mcp-tax
Audit the context tax of your MCP servers; toggle them off per session
mod-audit
Static supply-chain auditor for Claude Code Mods — local, offline, stdlib-only; update-diff risk reports
edit-guard
A Claude Code hook combo: block stale concurrent edits (pre-edit) + inject recorded decisions into new sessions (session-start)
mcp-runtime-audit
Local runtime security scanner for MCP servers — known-CVE checks, one-click fixes
subagent-budget
Hard budget caps for subagents — token/$ limits enforced by hooks, not just displayed
licenseproof
Check that a published Python artifact carries usable license information
entryprobe
Verify that a package's console_scripts entry points can actually start after install
wheelreach
Check that a package's declared Python support actually has installable release files
tagtruth
Check that a PyPI package's published versions actually have matching Git tags
review-bridge
Review secretary for a family noodle restaurant: Chinese briefings, bad-review alerts, English reply drafts — powered by a local Gemma model
casecrash
Find filenames in your git index that would collide on macOS or Windows checkouts
wheeltruth
Check that your built wheel/sdist actually contains everything the package needs
plan-shard
Split monolithic AI plans into executable shards; apply targeted feedback to one shard at a time
browser-buddy-mcp
MCP server that lets coding agents read pages through your real, logged-in Chrome (companion to the browser-buddy Chrome extension)
