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 agentmods add skills/evolplus/talos/data-lifecycle-contractsnpx skills add evolplus/talos --skill data-lifecycle-contractsgit clone --depth 1 https://github.com/evolplus/talosWhat 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 | $0.00084 | $0.03048 |
| Opus 5 | $0.00042 | $0.01524 |
| Sonnet 5 | $0.00017 | $0.00610 |
| Haiku 4.5 | $0.00008 | $0.00305 |
Grade A, and why
data-lifecycle-contracts 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 2d 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 — 148 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Data Lifecycle Contracts
When to use
You are the SA authoring docs/architecture.md (in design or extract mode). Your data model has columns that are written by one component and read by another to gate behavior. This skill prescribes how to identify those columns and document their write-ownership contract so downstream developers don't accidentally break the gate.
The motivating bug: A repository-sync service stamped last_synced_at = CURRENT_TIMESTAMP on every upsert during the discovery phase (a natural ORM-convenience pattern). The downstream WorkerPool's skip check read the same column to decide whether to re-process a repo: now - last_synced_at < SYNC_MIN_INTERVAL → skip. Result: every repo appeared "just synced" right after discovery, so every repo was always skipped. The data pipeline never ran. The discovery service wrote the column with one semantic ("we touched this row"); the worker read it with a different semantic ("last successful data collection"). No layer of the kit's discipline caught the mismatch because column-level write ownership sits between C3 (component responsibilities) and C4 (code-level columns) — neither layer documented it.
This skill exists so the SA explicitly hoists this contract up into the architecture.
Inputs and outputs
- Inputs: SRS §3.1 Domain Specification + §3.3 FRs (which name the data-mutating operations);
docs/architecture.md§3 Components (which name the components doing the mutations). - Outputs: Architecture §6 Cross-Component Data Contracts table; cross-references from the relevant FRs' Data Effects sub-section; gate-field write-prohibition constraints propagated to BE Dev / FE Dev
## Project Specializationby the Agent Generator.
What is a gate field?
A column whose read controls behavior in a component different from the one(s) that write it. Common patterns:
| Pattern | Read controls | Common columns |
|---|---|---|
| Skip / rate-limit gate | "Should I re-process this row?" | last_synced_at, last_run_at, next_eligible_at, cooldown_until |
| State machine gate | "What transition is allowed?" | state, status, phase, disposition |
| Eligibility gate | "Is this row eligible for X?" | is_active, is_verified, is_premium, eligible_until |
| Idempotency / dedup gate | "Have we already done this?" | processed_at, acknowledged_at, idempotency_key, dedup_hash |
| Version gate | "Is the data new enough?" | schema_version, etag, last_modified |
| Ownership / audit gate | "Who owns this and when was it touched?" | owner_id, updated_by, created_by (when used in authorization) |
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.
- 2d ago First seen · 148 lines · 84 tokens per session scan A f1c1fe3ba7c7
data-lifecycle-contracts is a skill published in the GitHub repository evolplus/talos (8 stars, last pushed 28d ago), licensed Apache-2.0. It adds 84 tokens to every session and 3,048 once invoked, about $0.0004 per session on Opus 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 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
agent-host-chat-contributions
Build and review cross-cutting agent-host chat behavior through lifecycle contributions. Use when adding turn lifecycle side effects, prompt or context injection, restored-history transformation, protocol-action observation, or when reviewing changes that add code to AgentSideEffects or AgentService.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.