Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/kora-projects/kora-skillsnpx agentmods add skills/kora-projects/kora-skills/kora-journalWrote 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/kora-projects/kora-skills/kora-journal)<a href="https://agentmods.dev/skills/kora-projects/kora-skills/kora-journal"><img src="https://agentmods.dev/badge/skills/kora-projects/kora-skills/kora-journal/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/skills/kora-projects/kora-skills/kora-journal"><img src="https://agentmods.dev/badge/skills/kora-projects/kora-skills/kora-journal.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 | $0.00062 | $0.02477 |
| Opus 5 | $0.00031 | $0.01239 |
| Sonnet 5 | $0.00012 | $0.00495 |
| Haiku 4.5 | $0.00006 | $0.00248 |
Grade A, and why
kora-journal 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 9d 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 — 298 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Kora Journal — Continuous Improvement for Kora Skills
Kora sub-skill — obey the kora-v1 meta rules on every task: R0 ensure
.kora-agent/docs+examples are cloned · R1 read this sub-skill before writing code · R2 Kora APIs only — no Spring/Micronaut/Quarkus, no invented annotations or config keys · R3 journal any incorrect Kora usage. Add comments/Javadoc only if asked.
Location: ~/.kora-journal/<project>/<module>/<YYYY-MM-DD>_slug.md
Format: Each entry is a separate Markdown file for easy management, export, and integration.
⚠️ READ FIRST — Purpose & Scope
Purpose: Journal for recording Kora Framework incorrect usage discovered during development — when the agent used Kora incorrectly and realized it or the user pointed it out.
⚠️ SCOPE — Kora Incorrect Usage ONLY:
| ✅ Record in Journal | ❌ Do NOT Record |
|---|---|
| Agent used wrong Kora annotation (self-realized or user-pointed) | Application business logic |
| Agent hallucinated non-existent Kora API | Project-specific domain rules |
| Agent misapplied Kora pattern (DI, AOP, config, etc.) | Temporary project workarounds |
| Agent violated Kora best practices from skills | UI/UX preferences |
| Skill documentation was unclear/wrong | Non-Kora framework issues |
Trigger: When YOU (agent) realize OR USER points out that you used Kora Framework incorrectly.
Why: Journal feeds skill improvements. Non-Kora entries clutter the journal and dilute its value.
Quick Start
# Add entry (creates separate .md file, tags auto-generated)
python kora-journal/scripts/kora_journal.py add "Fixed HTTP client example" \
--context "Implementing interceptor" \
--problem "Example missing error handling" \
--solution "Added try-catch and logging" \
--files kora-http-client/references/interceptors-reference.md
# Add entry with custom tags
python kora-journal/scripts/kora_journal.py add "OAuth2 token refresh" \
--context "..." --problem "..." --solution "..." --files ... \
--tags auth oauth2 client token
# Search journal by keywords (use AFTER reading references)
python kora-journal/scripts/kora_journal.py search "http interceptor auth" --limit 5
# Search by tags only (more precise)
python kora-journal/scripts/kora_journal.py search "auth oauth2" --by-tags
# View recent entries
python kora-journal/scripts/kora_journal.py list --limit 10
# Export pending entries from date
python kora-journal/scripts/kora_journal.py export --since 2026-05-01 --status pending
# Mark entry as integrated after applying to skills
python kora-journal/scripts/kora_journal.py integrate 2026-06-20_fixed-http-client.md
# Check status
python kora-journal/scripts/kora_journal.py status
What ships with it
4 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.
- 9d ago First seen · 298 lines · 62 tokens per session scan A 762e2cb62342
kora-journal is a skill published in the GitHub repository kora-projects/kora-skills (1 stars, last pushed 9d ago), licensed Apache-2.0. It adds 62 tokens to every session and 2,477 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 2026-08-31.
Other skills, from other repositories
frontmcp-extensibility
Use when extending FrontMCP beyond the core SDK by integrating external npm packages, libraries, or third-party services into providers and tools. Covers VectoriaDB for in-memory semantic and vector search (ML-based embeddings or TF-IDF keyword engines, with persistence) and the tamper-evident, hash-chained skill…
memory-consolidate
A memory-maintenance skill that stores a small number of durable, searchable facts and keeps the main memory file concise.
frontmcp-testing
Use for anything about testing FrontMCP servers: writing or running unit, integration, and E2E tests and reaching the 95%+ coverage bar. Covers Jest setup and coverage gating; unit-testing a ToolContext execute() with mock context, inputs, and Zod schema validation; testing resources and prompts; in-memory testing via…
session_logs
Search and analyse your own conversation history from session files. Use when: user references older conversations, asks what was said before, or needs historical context from past sessions. NOT for: current session messages (already in context), non-session files, or external logs.
persona-knowledge
Persistent, incremental, searchable persona knowledge base. Ingests data from Obsidian vaults, chat exports, X/Twitter archives, and more into a MemPalace-backed store with a Karpathy LLM Wiki knowledge layer. Exports training/ directories for persona-model-trainer.
memory
Cross-session memory that lets your persona remember, recall, and learn from past interactions. Memories persist across conversations and shape how you engage with the user over time.