Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add makifbaysal/tasktrooper --skill data-isolation-and-lifecyclegit clone --depth 1 https://github.com/makifbaysal/tasktrooperWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/makifbaysal/tasktrooper/data-isolation-and-lifecycle)<a href="https://agentmods.dev/skills/makifbaysal/tasktrooper/data-isolation-and-lifecycle"><img src="https://agentmods.dev/badge/skills/makifbaysal/tasktrooper/data-isolation-and-lifecycle/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/makifbaysal/tasktrooper/data-isolation-and-lifecycle"><img src="https://agentmods.dev/badge/skills/makifbaysal/tasktrooper/data-isolation-and-lifecycle.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00082 | $0.01902 |
| Opus 5.5 | $0.00033 | $0.00761 |
| Sonnet 5.5 | $0.00016 | $0.00380 |
| Haiku 4.5 | $0.00008 | $0.00190 |
Grade A, and why
data-isolation-and-lifecycle scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Data Isolation and Lifecycle
Overview
Endpoint checks protect one door. Data has many copies — a cache entry, a search document, a thumbnail, an export file, a log line, a backup, a queued job — and each copy has its own reader and its own retention. Isolation fails where a copy forgets who owns the data, or where a deleted or revoked record keeps working.
Core principle: pick one protected record the diff touches and follow it through every write, read, copy and state change. At each edge, name the code that enforces its owner. A tenant column is not that code.
1. A Tenant Field Is Not Isolation (CWE-639, CWE-863)
The owner column exists; the question is which query, policy or key enforces it on this path.
- Bypass clients: Supabase's service-role key or a Postgres role with
BYPASSRLSused in a request handler; a "system" repository that skips the tenant filter, called from a user-facing path. - Unscoped escapes: GORM
Unscoped()(it also drops the soft-delete filter), Railsunscoped, a Django manager that is not the filtered default, Hibernate filters that do not apply to native queries, Prisma middleware that a raw query skips. - Policy and query disagree: row-level security on the table but the new view, function (
SECURITY DEFINER), materialized view or aggregate reads around it; a join that brings in rows of another tenant through an unscoped relation.
-- ❌ SECURITY DEFINER runs as the function's owner; a table owner bypasses RLS
-- (unless FORCE ROW LEVEL SECURITY is set), so the caller's policy never applies
CREATE FUNCTION project_stats(p uuid) RETURNS TABLE(...) LANGUAGE sql SECURITY DEFINER
AS $$ SELECT ... FROM tasks WHERE project_id = p $$;
-- ✅ SECURITY INVOKER (the default), or filter on the caller's tenant inside the function
2. Keys and Namespaces Without the Tenant
Two principals collide on one logical key even though their records have separate owners:
- cache keys built from a user-chosen name (
report:+ name) or from an id that is only unique per tenant; - object-storage keys from the uploaded filename (
uploads/avatar.png) — one tenant overwrites or reads another's; - search document ids, deduplication keys, idempotency keys and lock names without the tenant;
- globally unique constraints that let one tenant squat or probe another tenant's slug, email or domain.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 12d ago First seen · 109 lines · 82 tokens per session scan A fc458a8692a7
data-isolation-and-lifecycle is a skill published in the GitHub repository makifbaysal/tasktrooper (121 stars, last pushed 7d ago), licensed Apache-2.0. It adds 82 tokens to every session and 1,902 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-15.
Other skills, from other repositories
embeddings
Vector embeddings with HNSW indexing, sql.js persistence, and hyperbolic support. 75x faster with agentic-flow integration. Use when: semantic search, pattern matching, similarity queries, knowledge retrieval. Skip when: exact text matching, simple lookups, no semantic understanding needed.
AgentDB Performance Optimization
Optimize AgentDB performance with quantization (4-32x memory reduction), HNSW indexing (150x faster search), caching, and batch operations. Use when optimizing memory usage, improving search speed, or scaling to millions of vectors.
AgentDB Vector Search
Implement semantic vector search with AgentDB for intelligent document retrieval, similarity matching, and context-aware querying. Use when building RAG systems, semantic search engines, or intelligent knowledge bases.
V3 Memory Unification
Unify 6+ memory systems into AgentDB with HNSW indexing for 150x-12,500x search improvements. Implements ADR-006 (Unified Memory Service) and ADR-009 (Hybrid Memory Backend).
ramp
Fetch and follow Ramp's published agent playbooks inside Paperclip, with mandatory approval gates for spend, incorporation, cards, account setup, and other financial actions.
agent-topology-optimizer
Agent skill for topology-optimizer - invoke with $agent-topology-optimizer.