agentmods.dev

base: Skill for Claude Code

.ai/agents/_template/skills/competences/journal/SKILL.md

journal is a skill for Claude Code from ai-swiss/base. It costs 29 tokens per session (934 once invoked), scanned A, original, Apache-2.0.

A session journal that stores notes about completed work and decisions in dated files. It acts as memory that an agent can read when continuing in a later conversation.

In plain words
What is it for?
Use it at the end of a workflow and when resuming work, to record actions, decisions, modified files, and follow-up tasks.
Why use it?
It reduces the need to reconstruct previous work from scratch. The required format also records unfinished items and files that were changed.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

This is ai-swiss/base's own configuration. It tells Claude Code how to work on base itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything base configures →

not rated 65repo +1 changed 1mo ago A scan SkillSpector: pass 29 tokens original Apache-2.0
View source ↗ ai-swiss/base a-i.swiss
Reuse

Borrowing it

Nothing to install: this file belongs to ai-swiss/base. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/ai-swiss/base/main/.ai/agents/_template/skills/competences/journal/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/ai-swiss/base

Made for: Claude Code.

Wrote 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.

agentmods badge for journal

README.md
[![agentmods](https://agentmods.dev/badge/skills/ai-swiss/base/journal/github.svg)](https://agentmods.dev/skills/ai-swiss/base/journal)
Your own site
<a href="https://agentmods.dev/skills/ai-swiss/base/journal"><img src="https://agentmods.dev/badge/skills/ai-swiss/base/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.

agentmods 80×15 button for journal

Your own site · 80×15
<a href="https://agentmods.dev/skills/ai-swiss/base/journal"><img src="https://agentmods.dev/badge/skills/ai-swiss/base/journal.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 29 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 934 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00029 $0.00934
Opus 5.5 $0.00012 $0.00374
Sonnet 5.5 $0.00006 $0.00187
Haiku 4.5 $0.00003 $0.00093

Measured 1mo ago against content hash 7ca3d73d98e8, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

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 1mo 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.

.ai/agents/_template/skills/competences/journal/SKILL.md · 87 lines

How it starts

The opening of the file, as written. The whole thing — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Journal de session

Le journal est la mémoire externe de l'agent d'une conversation à l'autre. Sans lui, chaque session repart de zéro; avec lui, l'agent reprend là où il s'était arrêté.

Quand écrire une entrée

À la fin de chaque process (chaque procédure invocable), l'agent écrit une entrée de journal. C'est l'ultime étape de tout process.

Où écrire

Emplacement: .ai/journal/YYYY-MM-DD_description.md

Exemples:

  • .ai/journal/2026-04-20_configuration.md
  • .ai/journal/2026-04-20_devis-favre.md
  • .ai/journal/2026-04-21_devis-mueller.md

Si le dossier .ai/journal/ n'existe pas encore, le créer avant la première entrée.

Format d'une entrée

# Session : [titre descriptif]
Date : YYYY-MM-DD
Agent : [nom-agent]
Skill : /[nom-du-process]

## Ce qui a été fait
- [action concrète 1]
- [action concrète 2]

## Fichiers créés ou modifiés
- chemin/vers/fichier1.md
- chemin/vers/fichier2.json

## Décisions
- [DECISION: choix | raison]

## À suivre
- [A VALIDER: élément en attente de confirmation]
- [A COMPLETER: information manquante]

Règles

  • Sections conditionnelles. N'inclure une section que si elle a du contenu. Jamais de section «Décisions» vide.
  • Concis. Le journal est un aide-mémoire, pas un rapport. À session courte, entrée courte.
  • Marqueurs dans le journal. Utiliser les marqueurs [DECISION], [A VALIDER], [A COMPLETER]: le journal se prête ainsi à la recherche au même titre que les documents générés.

Reprise de session

Quand l'utilisateur revient après une interruption («on en était où?», «bonjour», ou simplement en reprenant le travail), l'agent:

  1. Lit les entrées récentes dans .ai/journal/ (les 2-3 dernières)
  2. Résume l'état actuel: ce qui a été fait, ce qui reste à faire
  3. Propose la suite: traiter un [A VALIDER], compléter un [A COMPLETER], ou commencer un nouveau process

Cette reprise vaut aussi en cours de session: si tu ne peux plus citer le chemin du process actif (après un résumé, ou loin dans une longue conversation), rouvre l'AGENT.md et le SKILL.md actifs plutôt que de te fier au contexte courant.

Read the full file on GitHub · 87 lines

Changes

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.

  1. 1mo ago Changed · -2 lines 7ca3d73d98e8
  2. 1mo ago Changed 40d2eedc2c2c
  3. 2mo ago First seen · 89 lines · 29 tokens per session scan A 193b28824aab

Subscribe to this mod's changes

journal is a skill published in the GitHub repository ai-swiss/base (65 stars, last pushed 8d ago), licensed Apache-2.0. It adds 29 tokens to every session and 934 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 2026-08-30.

Memory and contextaiai-agentsclicognitive-sovereigntydigital-sovereigntygovernance
Related

journal compared with skills from other repositories

journal next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
journalai-swiss/baseSkill658d agoApache-2.0A29Claude Code
brain-ingestmindmuxai/brain.mdSkill594yesterdayApache-2.0A48Claude Code, Codex
mnemonmnemon-dev/mnemonSkill6936d agoApache-2.0A68Claude Code, Codex
memoryshobcoder/shobSkill5757d agoMITA146Claude Code, Codex
durable-session-stateZaxbyHub/opencode-swarmSkill518yesterdayMITA70Claude Code
sivtr-memoryAriestar/sivtrSkill255yesterdayApache-2.0A46Claude Code, Codex
save-learningcaliber-ai-org/ai-setupSkill1.3k1mo agoMITA71Claude Code, Codex