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/format-boundary-contractsnpx skills add evolplus/talos --skill format-boundary-contractsgit clone --depth 1 https://github.com/evolplus/talosWrote 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/evolplus/talos/format-boundary-contracts)<a href="https://agentmods.dev/skills/evolplus/talos/format-boundary-contracts"><img src="https://agentmods.dev/badge/skills/evolplus/talos/format-boundary-contracts.svg" alt="Measured on agentmods" 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 | $0.00090 | $0.04261 |
| Opus 5 | $0.00045 | $0.02131 |
| Sonnet 5 | $0.00018 | $0.00852 |
| Haiku 4.5 | $0.00009 | $0.00426 |
Grade A, and why
format-boundary-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 4d 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 — 166 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Format Boundary Contracts
When to use
You are the SA authoring docs/architecture.md (in design or extract mode). Your design has data flowing across two systems with different format contracts — typically: external system A (e.g., GitLab API) → product component → external system B (e.g., MySQL). Each system has its own input format requirements. The product component sits at the boundary and is responsible for the conversion even when both systems "look like" they handle the same conceptual type (e.g., datetime).
This skill is the format-conversion sibling to data-lifecycle-contracts (column write ownership). Where data-lifecycle-contracts covers when a value is written, format-boundary-contracts covers what shape the value must take at each boundary. Both contracts go in architecture.md §6; together they describe the data's full lifecycle across components.
The motivating bug: GitLab returned "merged_at": "2025-06-15T14:30:00Z" (ISO-8601 with T separator + Z suffix). The worker passed this verbatim to MySQL as a bound parameter for a DATETIME column. MySQL's DATETIME binary format only accepts 'YYYY-MM-DD HH:MM:SS' — it rejected the T and Z characters as syntax errors. The architecture had specified time_zone='+07:00' per connection (which controls interpretation of stored values) but never specified that the worker must strip T→space and Z→empty before binding (which controls the format of bound parameters). Adjacent concepts; opposite axes; nobody documented the format axis at architecture time. Every test, every mock, every DAL retry, every error wrapper silently passed the malformed value through.
Inputs and outputs
- Inputs:
docs/external-integrations/<system>.mdper integration (each one's published format), SRS data-mutating requirements (which fields move from where to where), existingdocs/architecture.mdif any. - Outputs: Architecture §6 format-contract rows for every data field that crosses a format boundary; per-FR
## Data Effectssub-sections reference the §6 rows; BE Dev / FE Dev specialization gains explicit "convert X→Y here" constraints from the Agent Generator extraction.
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.
- 4d ago First seen · 166 lines · 90 tokens per session scan A d2022d5a305e
format-boundary-contracts is a skill published in the GitHub repository evolplus/talos (8 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 90 tokens to every session and 4,261 once invoked, about $0.0005 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.
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.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
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…