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 complexity-reductiongit 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/complexity-reduction)<a href="https://agentmods.dev/skills/cody-w-tucker/cognitive-assistant/complexity-reduction"><img src="https://agentmods.dev/badge/skills/cody-w-tucker/cognitive-assistant/complexity-reduction/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/complexity-reduction"><img src="https://agentmods.dev/badge/skills/cody-w-tucker/cognitive-assistant/complexity-reduction.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 | $0.00066 | $0.02012 |
| Opus 5.5 | $0.00026 | $0.00805 |
| Sonnet 5.5 | $0.00013 | $0.00402 |
| Haiku 4.5 | $0.00007 | $0.00201 |
Grade A, and why
complexity-reduction 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 1mo 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 — 167 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Complexity Reduction
When To Use
Load this when any of these are in play:
- About to summarize, simplify, redesign, or hand off something that could sound informed while drifting from actual files, behavior, or operator
- A simplification is on the table and you cannot yet tell whether it removes real complexity or just renames it
- Output risks becoming structurally heavier than the task (extra layers, dependencies, branching, frameworks, citations, tool chatter, multi-voice prose)
- Tempted to claim "it should work" without a concrete before/after/confirm path
- Deliverable will be operated by someone specific — non-technical editor, coding agent, buyer who needs the point immediately
- User signal: "this seems overly complex," too many files, factory/if-tree smell, defensive scaffolding already covered by a library
- Structure has become harder to reason about than the problem it solves
Do Not Use
- Plain factual answers, small edits, or mechanical procedures where verification and usability are not in question
- Cases where adding structure is the actual job and already proven necessary
- Scope still unbound (no object/operator/acceptance) —
scope-framingfirst - Pure discovery-vs-commitment pacing / handoff polish —
boundary-handoff - Blind patch or fluency-without-ground drift mid-repair —
failure-recovery(may interrupt into this skill after diagnosis)
What This Owns
Structural simplification with truth-contact and operator fit — collapse unearned machinery while preserving the function that matters and leaving the next decision guesswork-free.
Does not own: initial bounding, mode routing, relational motive, or full diagnosis loops.
Standing rule from profile: earn every layer. Best practice is not justification. Cutting ceremony is not cutting rigor.
Two-Halves Test (Before Calling Work Done)
Strong work requires both halves; one without the other is unfinished:
- Simplify to the minimum form that preserves real utility. Remove unnecessary moving parts, but keep every piece of information needed to act safely — fit the operator who maintains or runs it.
- Then add enough concrete structure that the next decision needs no guesswork. Detail in the dimension that makes the main path obvious — not detail elsewhere that hides the main path.
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.
- 1mo ago First seen · 167 lines · 66 tokens per session scan A 9b2dab21c634
complexity-reduction is a skill published in the GitHub repository Cody-W-Tucker/Cognitive-Assistant (11 stars, last pushed 9d ago), licensed Apache-2.0. It adds 66 tokens to every session and 2,012 once invoked, about $0.0003 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 2026-08-30.
Other skills, from other repositories
autoreview
Structured code review through the shared OpenClaw agent-skills installation.
omh-code-review
This is an OMH code-review workflow skill, projected for Agent Skills hosts (Claude Code, Codex, Cursor, opencode, OpenClaw, pi).
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
explore-unknowns
Guide the user through a quadrant walk that maps the unknowns of a task — open by listing the known knowns, then work through known unknowns, unknown knowns, and unknown unknowns one stage at a time, ending with a complete four-quadrant map in the user's hands. Use when a request is ambiguous or underspecified, the…
asplos-writing-style
Use when drafting or revising ASPLOS prose — engineering the first two pages that rapid review actually reads, stating the cross-layer insight as one quotable sentence, structuring per-layer mechanism sections, writing bounded claims, and fitting everything into 11 self-contained pages that include figures and…
re0-merge
Review and land an external contribution the way this suite does: gate it against the thesis, land it with the author's credit intact, complete a new skill rather than merging it raw, then approve, credit, and explain before closing. Use when reviewing a pull request, as any collaborator or maintainer, not only the…