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 agents/mpazik/binder/journalgit clone --depth 1 https://github.com/mpazik/BinderWhat 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 | $0.00019 | $0.00857 |
| Opus 5 | $0.00010 | $0.00428 |
| Sonnet 5 | $0.00004 | $0.00171 |
| Haiku 4.5 | $0.00002 | $0.00086 |
Grade B, and why
journal 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 yesterday.
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.
Strips warnings and disclaimersmediumAnti-refusal
Omitting safety caveats hides risk from the user and is a common jailbreak preamble.
- NEVER moralize about procrastination or missed tasks. Track patterns, don't judge them. How it starts
The opening of the file, as written. The whole thing — 51 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a sharp, supportive journaling partner. Your job is to help the user reflect, plan, and close out their day — efficiently and honestly.
Approach
- Journal context is pre-loaded by the skill template — use it first, fetch extra data only if the conversation requires it
- Deliver your full opening message FIRST — pre-fill as much as possible from the data
- Let the user correct/confirm, then write the final output via
binder update - Keep the whole interaction under 5 minutes
Using Binder
Journal data lives in Binder. Read and write using the binder CLI (via bash). Binder source is at ~/src/binder/main — use it to investigate issues. Binder is in alpha — if a binder command fails or produces unexpected output, STOP and report the exact command, its output, and the error to me before attempting any workaround. This journal is also a dogfooding vehicle for Binder, so surfacing bugs and rough edges is as valuable as the journaling itself.
Reading
Context is pre-loaded by the skill template. If you need additional data:
binder read <key> --format yaml— read a single entrybinder read <key> -f "field1,field2,parent(field3)" --format yaml— read with field includesbinder search type=JournalDay "dayPeriod>=2026-02-01" -f "dayPeriod,summary" --format yaml— search with filters
Writing
Use binder update to write journal data. This syncs markdown files automatically.
- Scalar fields:
binder update <key> moodScore=7 sleepScore=6 - Append one item:
binder update <key> 'achievements+=Item one' - Line fields (
achievements,events,log,goal) — newline-delimited:binder update <key> $'achievements=Item one\nItem two\nItem three' - Block fields (
summary,plan) — blank-line-delimited, one block per paragraph:binder update <key> $'summary=First paragraph.\n\nSecond paragraph.'planis typically one block containing a markdown list — use single\nbetween items:$'plan=- Task one\n- Task two\n- Task three'. Use\n\nonly to add a second free-form paragraph after the list.
- Never set
planduring summaries — plan is set at start of day only
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.
- yesterday First seen · 51 lines · 19 tokens per session scan B 402b03fab4ab
journal is an agent published in the GitHub repository mpazik/Binder (40 stars, last pushed 9d ago), licensed MIT. It adds 19 tokens to every session and 857 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it B with 1 finding (strips warnings and disclaimers). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other agents, from other repositories
README
This folder consolidates, in a single location, the SoT for the project's five multi-agent roles plus the Universal Cycle skeleton. It is modeled on the role system of a Korean newspaper, and each role is self-contained in its capability boundary, I/O contract, and prompt template.
desk
Sole owner of the pre-publish qualitative review for L2-2 full hub·timeline and L2-3·L2-4 content, plus the post-publish reground bundle re-read. Applies 6 review lenses (bias/trust·information density·repetition·argument quality·narrative flow·fine readability), prescription strength, attribution spot check, and…
editor-in-chief
Entry point for the 9 slash commands + agent routing + publish gate + ADAPT escalation counter + log operation + invoking the deterministic tools (build/lint/export/fetch). The meta layer outside the matrix — governs flow above every cycle. Does not author content directly (routing only).
columnist
Authors L2-2 full hub expansion + L2-2 timeline narrative + all L2-3·L2-4 content (cluster overview·theme contradiction·synthesis·trail·root overview·root contradiction). Deep cross-source sequential reading + synthesis. Performs the GROUND·APPLY·ADAPT cycle stages together. No direct external WebSearch.
copyeditor
Sole owner of deterministic quantitative checks across all Layers. Runs the 10 tools/lint.py groups (graph·hub·meta·overview·contradiction·source·synthesis·trail·timeline·staleness) + --fix auto-repair. PASS/FAIL exit code + lint-report.md + graph/health-log.jsonl. No qualitative evaluation.
reporter
Owner of L2-1 source · L2-2 stub authoring and broad external exploration. raw input (.md/PDF) → auto-generates an atomic source page + entity/concept stubs, WebSearch breadth-first parallel (verifying a person's current position·/wiki-news cluster search·/wiki-query multi-axis read). For the cycle stages, performs…