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 scope-framinggit 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/scope-framing)<a href="https://agentmods.dev/skills/cody-w-tucker/cognitive-assistant/scope-framing"><img src="https://agentmods.dev/badge/skills/cody-w-tucker/cognitive-assistant/scope-framing/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/scope-framing"><img src="https://agentmods.dev/badge/skills/cody-w-tucker/cognitive-assistant/scope-framing.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 | $0.00052 | $0.01983 |
| Opus 5 | $0.00026 | $0.00992 |
| Sonnet 5 | $0.00010 | $0.00397 |
| Haiku 4.5 | $0.00005 | $0.00198 |
Grade A, and why
scope-framing 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 10d 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 — 136 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Scope Framing
When To Use
Load this when the request could be answered immediately but answering early would commit effort around hidden scope, hidden assumptions, or an unnamed operator. Typical triggers:
- A fix, recommendation, or design is asked for before the real artifact (codebase, component, schema, prompt, copy, lead, runtime behavior) has been looked at
- The task names a goal but not who has to run, maintain, or live with the result
- The work could expand indefinitely (configurability, layers, defensive checks, exhaustive discovery) with no clear stop condition
- A request sounds clean but leans on thin evidence or a jump from a few examples to a broad claim
- A messy, expert-dependent domain needs to become runnable machinery — structured workflow, simpler config, guided interface — rather than knowledge stuck in heads or chat
- Prompt mode is ambiguous: plan-first verbs mixed with act-now pressure
Do Not Use
- Object, target operator, and acceptance criteria are already clear — more framing is drag; execute
- Small, bounded, factual or mechanical tasks — short question, direct answer, no discovery pass
- Planning would be ritual rather than reducing real ambiguity or architectural risk
- Known failure mid-fix — use
failure-recovery/ diagnose path - Work already at handoff of a finished artifact — use
boundary-handoff - Mechanism already overbuilt and the job is collapse — use
complexity-reduction
What Is Being Protected
Not correctness in the abstract — decision-quality under real operating conditions: usability, legibility, and fit for the person or system that will actually run the output.
Structure is valued when it makes work inspectable; simplification is valued when it lowers hidden operating cost; detail is valued only when it changes the decision. Against: unearned depth, ungrounded planning, abstraction that stops the work from being directly understood, changed, or handed off.
He is not a planner by disposition. Once ambiguity is locally bounded and the next move is obvious, further analysis reads as friction. Scope framing exists to earn the right to move fast afterward — not to perform process.
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.
- 10d ago First seen · 136 lines · 52 tokens per session scan A d2f95d8e482d
scope-framing is a skill published in the GitHub repository Cody-W-Tucker/Cognitive-Assistant (11 stars, last pushed 23d ago), licensed Apache-2.0. It adds 52 tokens to every session and 1,983 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.