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/jaredlangleycc/nightshift-os/self-improvenpx skills add jaredlangleycc/nightshift-os --skill self-improvegit clone --depth 1 https://github.com/jaredlangleycc/nightshift-osWrote 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/jaredlangleycc/nightshift-os/self-improve)<a href="https://agentmods.dev/skills/jaredlangleycc/nightshift-os/self-improve"><img src="https://agentmods.dev/badge/skills/jaredlangleycc/nightshift-os/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 | $0.00127 | $0.03577 |
| Opus 5 | $0.00063 | $0.01788 |
| Sonnet 5 | $0.00025 | $0.00715 |
| Haiku 4.5 | $0.00013 | $0.00358 |
Grade B, and why
self-improve scanned grade B with 1 finding 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
find /Users/jmb/.claude/projects -name "*.jsonl" -mtime -1 -type f How it starts
The opening of the file, as written. The whole thing — 313 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Self-Improve
The daily learning loop. Run at end of day to make the OS smarter than it was yesterday.
Working-parent solopreneurs cannot afford for the same mistake to happen twice. Self-improve catches the corrections the user made, the friction the user pushed through, and the successful patterns the user discovered, then converts each into a memory entry or a proposed skill update.
Modeled on Jared's existing self-improve skill at /Users/jmb/.claude/skills/self-improve/SKILL.md. Adapted to the project-scoped NightShiftOS context.
When this skill triggers
Fire when the user:
- Runs
/self-improve - Says "self improve"
- Says "review my week"
- Says "daily learning"
- Says "review yesterday"
- Cron task fires (typically end of day, 10pm local)
For project-scoped use, prefer daily runs over weekly. Daily runs catch context while it is fresh.
Gate policy (DO NOT VIOLATE)
| Target | Mode |
|---|---|
Memory files (memory/*.md in this project) |
AUTO-APPLY |
| CLAUDE.md | PROPOSE ONLY |
Project skills (skills/*/*/SKILL.md) |
PROPOSE ONLY |
Hooks (.claude/settings.json) |
PROPOSE ONLY |
| New skill creation | PROPOSE ONLY |
| User-directed skill creation in same session | AUTO-APPLY (when the user says "build it", "create the skill", "ship the skill") |
| Voice / banned-phrase rules | Add to memory (auto), update voice-rules skill (propose) |
Decision log entries (decisions/*.md) |
AUTO-APPLY (these were already user-authored decisions) |
Auto-apply means: edit the file directly, log what changed in the report.
Propose only means: write the diff into the report under "Proposed", do NOT touch the file. The user reviews and says "apply" or "ship P1 P3 skip P2" or "reject all".
The sequence
Step 1: Pull recent transcripts
Look in /Users/jmb/.claude/projects/<encoded-project-path>/<session-id>.jsonl. Filter to files modified in the relevant time window:
find /Users/jmb/.claude/projects -name "*.jsonl" -mtime -1 -type f
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 · 313 lines · 127 tokens per session scan B 06fb250e82f6
self-improve is a skill published in the GitHub repository jaredlangleycc/nightshift-os (3 stars, last pushed 1mo ago), licensed MIT. It adds 127 tokens to every session and 3,577 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
brand
Brand context management for marketing sessions with continuity across conversations.
memory-recall
Search and recall relevant memories from past sessions via memsearch. Use when the user's question could benefit from historical context, past decisions, debugging notes, previous conversations, or project knowledge -- especially questions like 'what did I decide about X', 'why did we do Y', or 'have I seen this…
relevance-coarse-filter
Cheap, high-recall first-pass filter that removes obvious junk from a detector candidate pool before expensive story-origin research and PR judgment. Decides keep, monitoronly, or reject — never ranks, writes angles, verifies dates, or decides whether to pitch.
alive:session-history
Revive sessions (quick or heavy), browse, and search — 'what happened recently?', 'find the session where we discussed X', 'revive yesterday's session'. For single-session recall and multi-session browsing. If the human needs to merge multiple sessions into one working context or detect conflicts between parallel…
recall
Must be used at the start of any non-trivial task involving code changes, debugging, repo exploration, file inspection, or environment/tooling investigation to surface stored guidance before analysis or tool use.
cross-session-handoff
Read, write, snapshot, and lock .arcgentic/state.yaml across planner, dev, audit, and optional test sessions.