suivi-actions

suivi-actions is a skill for Claude Code from ai-swiss/base. It costs 20 tokens per session (1,239 once invoked), scanned A, original, Apache-2.0.

A process for extracting open actions and decisions from meeting notes and tracking who is responsible, by when, and with what status.

In plain words
What is it for?
Reviewing meetings or projects, preparing follow-ups, checking specific decisions, and finding markers such as confirmed decisions or items still needing approval.
Why use it?
It turns scattered follow-ups and unresolved points into a clear list that can be reviewed or used for reminders.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: built for aider.

Good fit Reviewing meetings or projects, preparing follow-ups, checking specific decisions, and finding markers such as confirmed decisions or items still needing approval.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/ai-swiss/base/suivi-actions
Install

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.

Any agent
npx skills add ai-swiss/base --skill suivi-actions
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 suivi-actions

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/ai-swiss/base/suivi-actions"><img src="https://agentmods.dev/badge/skills/ai-swiss/base/suivi-actions.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 20 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,239 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 $0.00020 $0.01239
Opus 5 $0.00010 $0.00620
Sonnet 5 $0.00004 $0.00248
Haiku 4.5 $0.00002 $0.00124

Measured 10d ago against content hash a034fc907990, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

suivi-actions 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 10d 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.

exemples/assistant-reunion/.ai/agents/assistant-reunion/skills/processes/suivi-actions/SKILL.md · 110 lines

How it starts

The opening of the file, as written. The whole thing — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Suivre les actions et décisions

Extraire les actions et décisions des comptes-rendus existants, dresser un état des lieux clair (qui fait quoi, pour quand, où en sont les choses) et aider à relancer ce qui reste ouvert.

Inputs

Demande à l'utilisateur (optionnel):

  • Le périmètre: toutes les réunions, ou un projet / une personne / une période en particulier?
  • L'objectif: faire un point général, préparer une relance, ou vérifier une décision précise?

Avant de commencer, vérifie que entreprise/identite.md est rempli: sinon, charge skills/processes/configuration/SKILL.md.

Lis la compétence skills/competences/metier-reunion/SKILL.md et la compétence skills/competences/marqueurs/SKILL.md.

Étapes

1. Rassembler les actions et décisions

Parcours les fichiers de reunions/ et le .ai/journal/. Repère:

  • les marqueurs [DECISION: ... | ...] (décisions confirmées)
  • les actions (tâche, responsable, échéance, statut) dans les tableaux d'actions
  • les marqueurs [A VALIDER: ...] et [A COMPLETER: ...] (éléments en suspens)
  • les marqueurs [ATTENTION: ...] (alertes)

Applique le périmètre demandé (projet, personne, période).

2. Classer par statut

Classe les actions par statut:

  • Ouvertes: à faire, échéance future ou non datée
  • En retard: échéance dépassée par rapport à la date du jour
  • Terminées: marquées comme faites
  • À compléter: responsable ou échéance manquant ([A COMPLETER])

3. Présenter l'état des lieux

Présente un tableau clair:

«Voici l'état des actions [périmètre]:

En retard

Action Responsable Échéance Réunion d'origine
[tâche] [nom] [date] [réunion]

Ouvertes

Action Responsable Échéance Réunion d'origine
[tâche] [nom] [date] [réunion]

À compléter (responsable ou échéance manquant)

Action Manque Réunion d'origine
[tâche] [A COMPLETER: responsable / échéance] [réunion]

Décisions récentes

  • [DECISION: ... | ...]

Souhaitez-vous que je prépare une relance, mette à jour un statut, ou complète un élément manquant?»

Read the full file on GitHub · 110 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. 10d ago First seen · 110 lines · 20 tokens per session scan A a034fc907990

Subscribe to this mod's changes

suivi-actions is a skill published in the GitHub repository ai-swiss/base (45 stars, last pushed 6d ago), licensed Apache-2.0. It adds 20 tokens to every session and 1,239 once invoked, about $0.0001 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.