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 agentmods add skills/bashbop/otito/otito-self-improvenpx skills add BASHBOP/otito --skill otito-self-improvegit clone --depth 1 https://github.com/BASHBOP/otitoWrote 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/bashbop/otito/otito-self-improve)<a href="https://agentmods.dev/skills/bashbop/otito/otito-self-improve"><img src="https://agentmods.dev/badge/skills/bashbop/otito/otito-self-improve.svg" alt="Measured on agentmods" 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 | $0.00097 | $0.01425 |
| Opus 5 | $0.00048 | $0.00713 |
| Sonnet 5 | $0.00019 | $0.00285 |
| Haiku 4.5 | $0.00010 | $0.00143 |
Grade A, and why
otito-self-improve 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 4d 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 — 146 lines — stays where its author put it; the contents beside it link to each section on GitHub.
otito self-evaluate + auto-improve
Close the loop when context_pack / otito context is a weak map: turn the miss into a labeled regression, fix the engine, prove it, then stop for commit approval.
Default autonomy (gated)
- Detect and score the gap.
- Add or update an accuracy eval case (fixture when possible; live-repo note when not).
- Implement the smallest ranking/extractor fix in
/Users/segzy/dev/otito. - Re-run targeted tests +
npm run eval:accuracy(or the skill script). - Report before/after. Do not commit or open a PR unless the user asks.
Do not silently lower corpus thresholds to make a bad pack pass.
When to run
- User says otito missed / was not useful / should self-improve.
- After a task where the agent needed grep because hotspots/primary files were wrong.
- After changing
src/lib/context-engine.js,src/lib/code-map/ast.js, or index cache version.
Inputs to capture
From the failed task, record:
| Field | Example |
|---|---|
query |
extend organisation branding to RSVP … emails |
repoPath |
/Users/segzy/dev/bashbop-api |
expectedPrimary |
src/email/email.service.ts |
expectedHotspots (optional) |
sendRsvpConfirmationEmail, resolveEventEmailBranding |
notExpectedTop (optional) |
dump of unrelated controllers that dominated |
If the user did not label expected files, infer from what the agent actually edited, then confirm in the report.
Procedure
1) Score the gap
Prefer the helper (from a otito checkout):
node /Users/segzy/dev/otito/codex/skills/otito-self-improve/scripts/score-gap.mjs \
--query "…" \
--path /path/to/repo \
--expect-primary "src/email/email.service.ts" \
--expect-hotspot "sendRsvpConfirmationEmail" \
--json
What ships with it
2 files 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.
- 4d ago First seen · 146 lines · 97 tokens per session scan A 518e8a1cc014
otito-self-improve is a skill published in the GitHub repository BASHBOP/otito (1 stars, last pushed today), licensed MIT. It adds 97 tokens to every session and 1,425 once invoked, about $0.0005 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 2026-08-31.
Other skills, from other repositories
hr-onboarding
A new-hire onboarding plan as a single page — first week schedule, buddy + manager intro, learning track, equipment checklist, and "you're set when…" outcomes. Use when the brief mentions "onboarding", "new hire", "first week plan", or "入职".
html-ppt-taste-brutalist
16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).
ligandmpnn
Inverse-fold a backbone with ligand, nucleic-acid, and metal context using LigandMPNN (Dauparas et al. 2023, github.com/dauparas/LigandMPNN). Reach for this skill to redesign the residues lining a binding pocket around a bound small molecule or cofactor, to design metal-coordinating sites where the geometry must be…
evo2
Score, embed, and generate DNA sequences with Evo 2, a long-context genomic foundation model. Use this skill when: (1) Computing per-nucleotide or per-sequence likelihoods for variant effect scoring, (2) Embedding genomic windows for downstream classification, (3) Generating DNA conditioned on a prefix, (4) Scoring…
package-author
当用户要把手头的工具打包/标准化成 pinvou 插件包时使用——包括纯技能(SKILL.md)、纯 MCP 服务或它们的组合包。用户说"打包/做成插件包/标准化这个工具/给我一个能上传的标准包/写 plugin.json/加个图标"等，或给了散乱脚本/目录要整理成可上传 zip 时，用本技能把内容规范成 plugin-protocol 标准包（补 plugin.json、补 mcp/manifest.json、补 SKILL.md、补图标、校验命名）。.
google-meet
Google Meet via gws: create spaces, fetch join links, list recordings.