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 Cody-W-Tucker/Cognitive-Assistant --skill boundary-handoffgit clone --depth 1 https://github.com/Cody-W-Tucker/Cognitive-AssistantWrote 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/cody-w-tucker/cognitive-assistant/boundary-handoff)<a href="https://agentmods.dev/skills/cody-w-tucker/cognitive-assistant/boundary-handoff"><img src="https://agentmods.dev/badge/skills/cody-w-tucker/cognitive-assistant/boundary-handoff/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/cody-w-tucker/cognitive-assistant/boundary-handoff"><img src="https://agentmods.dev/badge/skills/cody-w-tucker/cognitive-assistant/boundary-handoff.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 | $0.00067 | $0.02055 |
| Opus 5 | $0.00034 | $0.01027 |
| Sonnet 5 | $0.00013 | $0.00411 |
| Haiku 4.5 | $0.00007 | $0.00205 |
Grade A, and why
boundary-handoff 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 11d 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 — 159 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Boundary Handoff
When To Use
Load this when a task is about to change hands or change stage, and the right response depends on reading the boundary correctly:
- A rough draft is becoming an artifact someone else will use to act
- You are tempted to prescribe before inspecting the real thing
- A recommendation might outrun what was actually verified
- You are unsure whether to keep exploring or commit to a move
- You are about to add structure, layers, or process and aren't sure they earn their place
- Technical, revision-heavy, or execution-facing work: codebase exploration, architecture/config, debugging, design review, prompt/system work, agent workflows, lead enrichment, sales rewriting
- Preparing a spec or deliverable for a downstream agent or non-technical operator
Do Not Use
- Simple factual lookups, quick troubleshooting, one-off how-to: answer directly — no decomposition, no imposed format, no tightening loop
- Open-ended philosophical or phenomenological exploration: approximation permitted; don't force operational artifact standards without a physical artifact or bounded business parameter
- Initial scope still unnamed (object/operator/acceptance missing) — use
scope-framingfirst - Mechanism is simply overbuilt and needs collapse —
complexity-reduction - Response is drifting mid-work (blind patch, fluency without ground) —
failure-recovery
Core Reading: Speed Is Bought, Not Compromised
Locate rigor; do not average it. Speed and rigor resolve by which side of the line you are on, not by compromise.
| Side | Examples | Standard |
|---|---|---|
| Reversible / discovery | scout, probe, retrieve, test, rough draft, "for now" experiment | Fast, broad enough to orient, rough OK |
| Commitment / handoff | synthesis, recommendation, config that persists, sales copy, agent spec, anything operated/sold/built upon | Slow down, tighten, claims must hold, clarity mandatory |
Buy safe speed by spending cheaply on upfront discovery so the expensive moment is already de-risked.
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.
- 11d ago First seen · 159 lines · 67 tokens per session scan A 472c77d3f808
boundary-handoff is a skill published in the GitHub repository Cody-W-Tucker/Cognitive-Assistant (11 stars, last pushed 24d ago), licensed Apache-2.0. It adds 67 tokens to every session and 2,055 once invoked, about $0.0003 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 2026-08-30.
Other skills, from other repositories
f19-steal-peace-in-chaos
A practice for staying calm during busy or noisy periods by regularly setting aside quiet time and building a steady inner routine.
runbook-authoring
Write runbooks that a sleepy oncall engineer at 3am can actually follow. Invoke when shipping anything pageable, or when a runbook is stale after a postmortem.
observability
Observability, Monitoring & SRE: Comprehensive guide for implementing observability (logs, metrics, traces), setting up monitoring and alerting, defining SLOs/SLIs/SLAs, creating dashboards, and incident detection. Use whenever the user mentions 'observability', 'monitoring', 'alerting', 'logging', 'metrics'…
chaos-engineering
Chaos Engineering: Designs and reviews resilience testing strategies — fault injection, game days, failure mode analysis, and blast radius assessment. Covers chaos experiments for distributed systems, database failures, network partitions, and dependency outages. Use when the user mentions chaos engineering…
incident-postmortem
Incident Response & Postmortem: Creates blameless postmortem documents and incident response runbooks. Use this skill whenever the user wants to write a postmortem, incident report, root cause analysis (RCA), create an incident runbook, document an outage, or analyze what went wrong in production. Trigger when the…
feature-flags
Feature flag strategies, rollout patterns, kill switches and flag lifecycle management.