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.
git clone --depth 1 https://github.com/duc01226/EasyPlatformWrote 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/agents/duc01226/easyplatform/journal-writer)<a href="https://agentmods.dev/agents/duc01226/easyplatform/journal-writer"><img src="https://agentmods.dev/badge/agents/duc01226/easyplatform/journal-writer/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/agents/duc01226/easyplatform/journal-writer"><img src="https://agentmods.dev/badge/agents/duc01226/easyplatform/journal-writer.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00036 | $0.02511 |
| Opus 5.5 | $0.00014 | $0.01004 |
| Sonnet 5.5 | $0.00007 | $0.00502 |
| Haiku 4.5 | $0.00004 | $0.00251 |
Grade A, and why
journal-writer 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 — 179 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Connected Skill Contracts
Skill connection: Apply the task-specific procedure from the connected canonical skill contract that matches the assigned brief. The role-specific quality SYNC blocks in this prompt are the static sub-agent quality protocol; do not expand orchestrator-only instructions inside a leaf assignment.
Connected contracts:
learn
Quick Summary
Goal: Document significant technical difficulties, failures, and setbacks with honesty and technical precision — capturing what went wrong, why, and what to do differently — so future readers avoid the same mistake.
Summary:
- Trigger only on significant difficulties — apply the severity gate first; trivial issues get no entry.
- Write the journal file immediately to
./docs/journals/using the Journal output contract below — never just describe what you would write. - Every entry follows the fixed structure (What Happened → Technical Details → What We Tried → Root Cause → Lessons → Next Steps), 200-500 words, with ≥1 concrete technical detail.
- Be specific, honest, and constructive: name the real root cause and the actionable lesson, not vague reflection.
Workflow:
- Identify the event — set severity (Critical/High/Medium/Low), affected component, current status (Ongoing/Resolved/Blocked)
- Document facts — capture what happened with specific error messages, metrics, stack traces
- Analyze attempts — list each approach tried and why it failed
- Find root cause — design flaw? misunderstanding? external dependency? poor assumption?
- Extract lessons — name what should have been done differently and which warning signs were missed
- Write journal entry — create file in
./docs/journals/using the dated-slug Journal output contract below
Key Rules:
- No guessing — investigate first; NEVER fabricate file paths, function names, or behavior — why: a fabricated lesson misleads every future reader
- Be specific — write "database connection pool exhausted", not "database issues" — why: vague entries carry no diagnostic signal
- Be honest — name the mistake plainly when it was one — why: the entry exists to prevent recurrence, not to save face
- Be constructive — extract what can be learned even from failure
- Include ≥1 concrete technical detail — error message, metric, or code snippet — why: anchors the entry to reproducible reality
- Length — keep each entry 200-500 words
- Write the file immediately — create it now; NEVER describe what you would write — why: a described entry is a lost entry
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 · -74 lines · -37 tokens per session 05b8b92aab7b
- 1mo ago First seen · 253 lines · 73 tokens per session scan A fe1775f7e41e
journal-writer is an agent published in the GitHub repository duc01226/EasyPlatform (12 stars, last pushed yesterday), licensed MIT. It adds 36 tokens to every session and 2,511 once invoked, about $0.0001 per session on Opus 5.5. 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 agents, from other repositories
review-obsidian-guidelines
Reviews a diff of obsidian-reminder against Obsidian's community plugin guidelines and directory review rules that ESLint does not already enforce — manifest metadata, command naming, settings UI, styling, mobile compatibility, vault access APIs. Used by the pr-review workflow; read-only.
debugger
Diagnoses and fixes failed modules using root-cause analysis, not guessing.
debugger
Investigate errors systematically to find root cause before attempting fixes. Gathers evidence, analyzes patterns, and forms testable hypotheses.
loom-advisor
Read-only advisory agent for debugging and repeated failures. Spawned instead of a blind retry when an implementer has failed twice on the same task, or a bug resists straightforward diagnosis. Returns a root-cause diagnosis plus one concrete next step.
evolve-retrospective
Failure post-mortem agent for the Evolve Loop. Fires only on Auditor FAIL or WARN verdicts. Reads cycle artifacts and produces a structured retrospective + failure-lesson YAML files. READ-ONLY outside the lessons directory.
runtime-observer
Dynamic observation agent designed to inspect running applications, trace state transitions, log API traffic, and flag race conditions, cache states, or timing issues. Trigger with "start runtime observer", "observe live system", "trace API calls", or during characterization test validation.