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/ripemangobox/bite/write-daily-lognpx skills add RipeMangoBox/BITE --skill write-daily-loggit clone --depth 1 https://github.com/RipeMangoBox/BITEWrote 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/ripemangobox/bite/write-daily-log)<a href="https://agentmods.dev/skills/ripemangobox/bite/write-daily-log"><img src="https://agentmods.dev/badge/skills/ripemangobox/bite/write-daily-log.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 | $0.00067 | $0.01282 |
| Opus 5 | $0.00034 | $0.00641 |
| Sonnet 5 | $0.00013 | $0.00256 |
| Haiku 4.5 | $0.00007 | $0.00128 |
Grade A, and why
write-daily-log 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 — 151 lines — stays where its author put it; the contents beside it link to each section on GitHub.
write-daily-log — Evidence-Driven Daily Research Log
Write a daily research log that captures facts which change future decisions, not a chronological activity dump.
Core Principle
Find evidence that changes future judgment → compress into log structure.
Only write content that satisfies at least one:
- Changes route/decision
- Changes experiment calibration or comparability
- Affects reproducibility
- Produces a concrete next action
- Is the day's most important quantitative result
Trigger
- User says "写日志", "日报", "write daily log", "update daily summary"
- User specifies a target file (e.g.
DailySummary/2026-04-15.md) - End of a long research session when user asks to wrap up
Procedure
Phase 1: Determine Target File
- If user specifies a file path → use it
- Else →
DailySummary/<today's date>.md - Read the target file if it exists; inherit its structure, tone, field names, and granularity
- If file doesn't exist → use TEMPLATE.md as skeleton
Phase 2: Collect Evidence
Evidence comes from two channels: conversation context and local persistent changes.
A. Conversation Context (current session)
Scan in priority order:
- User's explicit goals and requests this session
- Upper-level docs read this session (roadmap, experiment spec, prior summaries)
- New artifacts produced (eval yamls, metrics, new code, new docs)
- Key numbers verified or computed
- Engineering issues exposed or fixed
- Unresolved items and risks
B. Local Persistent Changes (cross-session)
Since the agent cannot access other sessions' history, use git and filesystem signals:
# 1. Find all git repos under the workspace
find <workspace_root> -maxdepth 3 -name ".git" -type d 2>/dev/null
# 2. For each repo, collect today's changes
git -C <repo> log --oneline --since="<today> 00:00" --until="<tomorrow> 00:00" --all
git -C <repo> diff --stat HEAD~5 # recent diff summary
git -C <repo> diff --name-only HEAD~5 # changed file list
# 3. Check uncommitted work
git -C <repo> status --short
# 4. Find today's new/modified artifacts
find <workspace_root> -name "*.yaml" -o -name "*.md" -o -name "*.csv" -o -name "*.log" | \
xargs ls -lt 2>/dev/null | head -30
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.
- 4d ago First seen · 151 lines · 67 tokens per session scan A 1d26e341f288
write-daily-log is a skill published in the GitHub repository RipeMangoBox/BITE (60 stars, last pushed 22d ago), licensed MIT. It adds 67 tokens to every session and 1,282 once invoked, about $0.0003 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 2026-08-30.
Other skills, from other repositories
compile-wiki
Merge source summaries into durable concept pages with backlinks, index entries, and explicit open questions.
ingest-sources
Review newly ingested raw sources and draft or update source summary notes in notes/Sources/.
qa-agent
Answer questions from the vault, then file durable insights back into the knowledge base.
research-workflow
Manage resumable research runs under research/ and coordinate the collect, review, report, import, and archive steps.
lint-heal
Scan the vault for contradictions, unsupported claims, structural weaknesses, and missing pages, then repair what is safe.
render-output
Convert vault content into downstream outputs like memos, reports, slide outlines, diagrams, and plot specifications.