agentmods.dev

base: Skill for Claude Code

.ai/agents/createur-agent/skills/processes/ameliorer-agent/SKILL.md

ameliorer-agent is a skill for Claude Code from ai-swiss/base. It costs 16 tokens per session (1,758 once invoked), scanned A, original, Apache-2.0.

A workflow for improving an existing software agent by adding tasks, domain knowledge, or behavior changes.

In plain words
What is it for?
Use it to inspect an agent, explain what it currently does, gather the requested changes, and add or update its processes and knowledge.
Why use it?
It helps identify whether an agent needs a new workflow, more information, or corrections to its current structure.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: reads .claude/ paths; mentions Claude Code.

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 16 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/createur-agent/skills/processes/ameliorer-agent/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 ameliorer-agent

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/ai-swiss/base/ameliorer-agent"><img src="https://agentmods.dev/badge/skills/ai-swiss/base/ameliorer-agent.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 16 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,758 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 $0.00016 $0.01758
Opus 5.5 $0.00006 $0.00703
Sonnet 5.5 $0.00003 $0.00352
Haiku 4.5 $0.00002 $0.00176

Measured 1mo ago against content hash 4b3c01a204ce, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

ameliorer-agent 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/createur-agent/skills/processes/ameliorer-agent/SKILL.md · 149 lines

How it starts

The opening of the file, as written. The whole thing — 149 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Améliorer un agent

Enrichir ou modifier un agent existant: lui ajouter des procédures, des connaissances, corriger ses comportements, ajuster sa structure.

Inputs

Demande à l'utilisateur:

  • Quel agent améliorer: liste les agents dans .ai/agents/ (en excluant _template/ et createur-agent/)
  • Ce qui manque ou ne fonctionne pas: description en langage naturel

Étapes

1. Comprendre l'agent existant

Lis l'AGENT.md de l'agent visé, puis résume-le à l'utilisateur:

«Voici ce que fait actuellement votre assistant [nom]:

  • Rôle: [description]
  • Procédures: [liste des process]
  • Connaissances: [liste des compétences]
  • Documents: [liste des templates]

Que souhaitez-vous modifier ou ajouter?»

2. Diagnostiquer le besoin

Selon ce que dit l'utilisateur:

«Il manque une procédure»:

«D'accord, décrivez-moi cette tâche. Quelles sont les étapes quand vous la faites aujourd'hui?» → Créer un nouveau process dans skills/processes/

«Il ne connaît pas assez mon domaine»:

«Quelles informations lui manquent? Quelles erreurs fait-il par méconnaissance?» → Créer une nouvelle compétence dans skills/competences/ ou enrichir une existante

«Il ne produit pas le bon document»:

«À quoi devrait ressembler le résultat idéal?» → Créer ou modifier un template

«Le comportement n'est pas bon»:

«Qu'est-ce qu'il fait qui ne vous convient pas?» → Ajuster AGENT.md (routage, philosophie, garde-fous)

«Il ne doit jamais pouvoir faire X», ou la personne demande un hook, une permission:

«Que coûterait une seule fois où il le ferait?» → Poser un verrou (voir «Garde-fous» dans architecture-agent): mettre l'information hors d'atteinte, ou proposer une permission avec le bac à sable de l'outil, ou un hook (pour Claude Code, .claude/settings.json; voir outils-connus). Un hook reste simple et rapide, sans appel de modèle. Au test, essaie l'action interdite une fois sur une cible sans conséquence, par chaque chemin (l'outil d'écriture, une commande, une copie de fichier): seul un refus de l'outil compte.

Read the full file on GitHub · 149 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 · +10 lines 4b3c01a204ce
  2. 1mo ago Changed · +17 lines 4eb2685f1ef7
  3. 2mo ago First seen · 122 lines · 16 tokens per session scan A 6eba7bcd0923

Subscribe to this mod's changes

ameliorer-agent is a skill published in the GitHub repository ai-swiss/base (65 stars, last pushed 8d ago), licensed Apache-2.0. It adds 16 tokens to every session and 1,758 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.

Building agentsaiai-agentsclicognitive-sovereigntydigital-sovereigntygovernance
Related

ameliorer-agent compared with skills from other repositories

ameliorer-agent next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
ameliorer-agentai-swiss/baseSkill658d agoApache-2.0A16Claude Code
complianceericrisco/rsc-harnessSkill5032d agoMITA96Claude Code, Codex
wallet-cliBofAI/skillsSkill1644d agoMITA92Codex
vaultjoelhooks/joelclawSkill65yesterdaynoneA82Claude Code
feishuHmbown/CodeWhaleSkill41k5d agoMITA33Claude Code, Codex
interviewHmbown/CodeWhaleSkill41k5d agoMITA40Claude Code, Codex
atmos-validationcloudposse/atmosSkill1.4kyesterdayApache-2.0A31Claude Code