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 oddyblue/Less-Is-More-Skill --skill less-is-moregit clone --depth 1 https://github.com/oddyblue/Less-Is-More-SkillWrote 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/oddyblue/less-is-more-skill/less-is-more)<a href="https://agentmods.dev/skills/oddyblue/less-is-more-skill/less-is-more"><img src="https://agentmods.dev/badge/skills/oddyblue/less-is-more-skill/less-is-more/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/oddyblue/less-is-more-skill/less-is-more"><img src="https://agentmods.dev/badge/skills/oddyblue/less-is-more-skill/less-is-more.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 | $0.00069 | $0.01203 |
| Opus 5.5 | $0.00028 | $0.00481 |
| Sonnet 5.5 | $0.00014 | $0.00241 |
| Haiku 4.5 | $0.00007 | $0.00120 |
Grade A, and why
less-is-more 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 — 55 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Less Is More
A way of working for every change, not a cleanup mode: leave the project smaller and simpler than it would otherwise be, without losing anything the app needs. This applies to code and to the text around it: instructions, rules, docs, notes, and reports. Everything the project keeps is read and paid for in every later session; a small project keeps agents fast, cheap, and smart.
Measure in moving parts first, then lines. Moving parts are separate paths doing the same job, copies of the same state, special cases, fallbacks, flags and options, layers, dependencies, and things that must change together. Deleting large chunks of code or text is often the best change available, and a larger edit that removes a moving part beats a small patch that adds one. Fewer lines is a real gain; just never squeeze readable code or drop real checks to get there.
Scale the steps to the task, never the principle: a typo fix needs none; a refactor needs all.
Before editing
Find where the behavior is actually decided and work there, not where the symptom shows up. Most unnecessary code comes from fixing the wrong thing, so try once to prove your diagnosis wrong before acting on it. Where logs or recorded data exist, look at what actually happened instead of reasoning about it.
Then consider, in order: no edit, delete, merge, replace, and only then add the smallest thing that fully works. Look for what already does the job — an existing function, pattern, or platform feature — before writing a new one. A verified "no change needed" is a good result.
For a replacement or cleanup, name exactly what will go: the functions, branches, files, or settings. Afterward, check that they are actually gone.
While editing
Replace; don't layer. When new behavior supersedes old behavior, delete the old path. Don't keep it behind a flag, mode, guard, fallback, or wrapper unless something real still depends on it — a named client, a saved data format, an app or server version still in use — and then keep it in one place.
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.
- 1mo ago Changed · -6 lines · -6 tokens per session 4fb923c44132
- 1mo ago First seen · 61 lines · 75 tokens per session scan A 9ef8c73648f7
less-is-more is a skill published in the GitHub repository oddyblue/Less-Is-More-Skill (2 stars, last pushed 1mo ago), licensed MIT. It adds 69 tokens to every session and 1,203 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 2026-08-31.
Other skills, from other repositories
code-context
How to answer codebase questions with the code-context MCP tools (search, sql, reindex): ranked hybrid keyword+semantic search, relevance-ranked SQL aggregation over the index, and index lifecycle. Use when a question spans many files ("how does X work", "where is Y handled"), when ranking or counting code by topic…
support-ticket-triage
Triage support tickets by pulling helpdesk context, searching issue trackers and knowledge bases in parallel, classifying the issue, and giving reps a recommended next action.
tapp
Use Tapp to see, drive, explore, and verify real application surfaces on iOS simulators, Android emulators/devices, or the web. Use when a user asks an agent to test an app or UI change, find bugs, inspect or screenshot a screen, exercise a journey, create a replayable flow, gather release evidence, run the…
recovery
Handle blocked verification outcomes.
fix-issue
Fix a GitHub issue end-to-end. Use when given an issue number to fix, implementing bug fixes, or addressing reported problems.
debugging-loop
Systematic reproduce-isolate-fix-verify loop for bugs, test failures, and unexpected behavior. Use when something is broken and the cause is not yet known.