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 OutlineDriven/outline-driven-development --skill debloat-respect-richnessgit clone --depth 1 https://github.com/OutlineDriven/outline-driven-developmentWrote 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/outlinedriven/outline-driven-development/debloat-respect-richness)<a href="https://agentmods.dev/skills/outlinedriven/outline-driven-development/debloat-respect-richness"><img src="https://agentmods.dev/badge/skills/outlinedriven/outline-driven-development/debloat-respect-richness/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/outlinedriven/outline-driven-development/debloat-respect-richness"><img src="https://agentmods.dev/badge/skills/outlinedriven/outline-driven-development/debloat-respect-richness.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00038 | $0.00827 |
| Opus 5 | $0.00019 | $0.00413 |
| Sonnet 5 | $0.00008 | $0.00165 |
| Haiku 4.5 | $0.00004 | $0.00083 |
Grade A, and why
debloat-respect-richness 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 3d 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 — 41 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Debloat respect richness
Contract
| Field | Bound contract |
|---|---|
| Trigger | User asks to tighten verbose-but-correct prose without a full rewrite |
| Authority | Reversible local: writes only the named artifact, cutting words in place; rollback is version control. No remote mutation. |
| Side effect | Local write to the target artifact only; no re-derivation, no move to another home |
| Done | Every load-bearing claim present before remains after; the result reads as intentionally terse, not amputated; genuine duplication or drift is handed off instead of force-compressed |
Inputs
- Required: the target artifact, a file path or pasted prose that is correct and current but has grown verbose or patched-over.
- Optional: a note flagging which sections are human-facing teaching or orienting prose whose accessibility earns its length.
Procedure
- Pin the artifact and read it end to end. Record one line per section stating the load-bearing content that must survive the pass. Done when: every section has a one-line load-bearing-content record.
- Distinguish bloat from content. Bloat is padding that adds length without meaning: a qualifier or parenthetical the sentence works without, a fused sentence carrying three ideas, an enumeration where a rule and short list would do, a point restated nearby, or litigation history where the rule alone suffices. Done when: bloat is distinguished from load-bearing content in every section.
- Compress in place: cut the padding, split the fused sentence or drop its dead clause, collapse the wall, keep a repeated point once. Move nothing to another artifact and re-derive nothing. Done when: padding is cut in place with nothing moved or re-derived.
- Preserve every load-bearing claim, a rule, fact, constraint, or example that carries weight. If cutting a word would lose one, keep the word. Done when: every load-bearing claim present before remains after the pass.
- Respect intended richness: human-facing prose meant to teach or orient (a quickstart, a worked example) earns its length. Compress the bloat, not the accessibility. Done when: human-facing teaching prose is preserved at its earned length.
- When the bloat is really duplication across artifacts, or the content has drifted stale, stop and name it: hand duplication to the appropriate deduplication work and drift to the appropriate rewrite work. This skill only tightens; it does not dedup or rewrite. Done when: duplication or drift is named and handed off, or no misclassification is found.
- Re-read cold and cut again; the first pass always leaves some. Done when: a cold re-read finds no remaining bloat.
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.
- 3d ago Changed · -20 tokens per session 44ed38dbdbfe
- 5d ago First seen · 41 lines · 58 tokens per session scan A 62e7d6da60e5
debloat-respect-richness is a skill published in the GitHub repository OutlineDriven/outline-driven-development (52 stars, last pushed 4d ago), licensed Apache-2.0. It adds 38 tokens to every session and 827 once invoked, about $0.0002 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 2026-09-03.
Other skills, from other repositories
audit-project
Run an iterative multi-agent code audit until critical and high findings are resolved. Use when the user says "audit my code", "find all the bugs", "deep code audit", "iterative review", or "review until clean".
duet
Use when the user invokes /duet, says "pair with me", or faces aesthetic, architectural, or irreversible decisions.
goal-prompt-drafting
Use when asked to draft copy-ready /goal objectives for long-running agents; returns one normalized one-line objective with measurable end state, grounded proof, easy-out invariants, a stop clause, and a Missing list. Not for source or remote-system changes.
handoff-prompt
Use when the user asks for a handoff, delegation, or clipboard-ready prompt for another agent: a standalone path-free prompt copied to the clipboard, confirmed by title. Not for session-snapshot briefs — use handoff; never remote, credential, publish, deploy, or irreversible.
publish-branch
Use when asked to publish the checked-out branch: commit and push it on whatever branch it is, the default branch included. Not for creating branches, PRs, force pushes, or pushing any other branch; when the request excludes the default branch, use commit-push-current.
snippet-image-rendering
Use when the user explicitly names snipgrapher and wants code rendered to a polished PNG, SVG, or WebP at an explicit local path. Probes the installed CLI for supported flags and writes only the named image file. Not for other renderers, publishing, or remote actions.