TeaQL Agent Kit is a development harness that places an executable domain model between a coding agent's requirements and its implementation. It evaluates and repairs that model, generates typed API boundaries, and guides the agent toward implementing and verifying software within those constraints. The catalogue entries provide the kit's agent, skill, and instruction workflows.
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 teaql/teaql-agent-kit --skill context-exclusiongit clone --depth 1 https://github.com/teaql/teaql-agent-kitWrote 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/teaql/teaql-agent-kit/context-exclusion)<a href="https://agentmods.dev/skills/teaql/teaql-agent-kit/context-exclusion"><img src="https://agentmods.dev/badge/skills/teaql/teaql-agent-kit/context-exclusion/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/teaql/teaql-agent-kit/context-exclusion"><img src="https://agentmods.dev/badge/skills/teaql/teaql-agent-kit/context-exclusion.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 | $0.00041 | $0.00433 |
| Opus 5.5 | $0.00016 | $0.00173 |
| Sonnet 5.5 | $0.00008 | $0.00087 |
| Haiku 4.5 | $0.00004 | $0.00043 |
Grade A, and why
context-exclusion 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 today.
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.
What it actually says
Generated context exclusion
Use the packaged scripts/markers.mjs entry point to maintain .agent-no-read.md.
Resolve that script relative to this skill directory; it uses the package's
compiled CLI runtime (or source modules in a checkout), so keep the installed
Agent Context Kit layout intact.
Run from the project root with an explicitly approved project-relative manifest:
agent-context-markers apply --manifest context-markers.json
agent-context-markers check --manifest context-markers.json
agent-context-markers generate --manifest context-markers.json
If the package bin is unavailable, invoke the resolved script with node and the
same arguments. No cwd, target-directory, guidance-text or shell-command overrides
are accepted. apply creates or updates markers, check performs no writes, and
generate runs the manifest's fixed generator and restores snapshotted markers in
finally, including after command failure or cancellation.
Use existing user/host authorization for the manifest and target directories; this skill does not authorize arbitrary configuration changes or removal of markers. Keep the manifest and Markdown guidance outside every generated output directory. Put stable interface locations, editable source locations and build/test guidance in the Markdown source. Do not copy implementation details into guidance.
In the dedicated Pi harness, call an already configured fixed build/generation
operation that embeds this script or its SDK helper. This skill does not install a
model-controlled maintenance tool, enable Bash, or bypass the tool allowlist. Treat
maintenanceFailed as a failed operation even if generation succeeded; verify or
repair the marker state through the authorized maintenance entry point before
continuing model access. Do not manually read excluded source to diagnose failure.
Read the maintenance guide for manifest format, exit codes, regeneration limits and the runnable end-to-end example.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- today First seen · 42 lines · 41 tokens per session scan A 2bcda06b7c16
context-exclusion is a skill published in the GitHub repository teaql/teaql-agent-kit (2,818 stars, last pushed yesterday), licensed MIT. It adds 41 tokens to every session and 433 once invoked, about $0.0002 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 2026-10-24.
Other skills, from other repositories
lane-memory
A file-based store for durable project facts that cannot be reliably inferred from source code or its module map.
winnow
How to read winnow stubs in tool results. A block marked "[winnow] ... hidden" was judged unlikely to matter for the current task and replaced with a short summary plus a recall key; call winnowrecall to restore it. Use when a tool result contains "[winnow]" lines or when winnowrecall / winnowstats tools are available.
catchup
Restore context after /clear by summarizing recent work and project state.
memory
A session-memory tool with three layers: agent notes, requirement memories, and overall project memory. The description does not specify how these memories are stored or managed.
summary
A skill that writes a summary of the current conversation to a daily memory file before work ends.
minimax-m3-long-context
How to use MiniMax M3's 1M-token MSA context productively: what to load vs. compress, when to retrieve vs. ingest, how to keep skills shallow in the always-on prompt and deep in skills, and how to plan retention across iterations. Load when the task might exceed 200K tokens, when the user asks to "keep all of this in…