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.
curl -O https://raw.githubusercontent.com/ai-swiss/base/main/.ai/agents/concierge-base/skills/processes/signaler-une-friction/SKILL.mdgit clone --depth 1 https://github.com/ai-swiss/baseWrote 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/ai-swiss/base/signaler-une-friction)<a href="https://agentmods.dev/skills/ai-swiss/base/signaler-une-friction"><img src="https://agentmods.dev/badge/skills/ai-swiss/base/signaler-une-friction/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/ai-swiss/base/signaler-une-friction"><img src="https://agentmods.dev/badge/skills/ai-swiss/base/signaler-une-friction.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00043 | $0.00739 |
| Opus 5 | $0.00022 | $0.00369 |
| Sonnet 5 | $0.00009 | $0.00148 |
| Haiku 4.5 | $0.00004 | $0.00074 |
Grade A, and why
signaler-une-friction 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 12d 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.
What it actually says
Signaler une friction
Une friction consignée est un amendement de process qui s'ignore encore. Ce process réunit le
contexte essentiel, puis inscrit l'entrée dans le journal de terrain (.ai/feedback/): on crée,
on ne modifie jamais. C'est le détecteur de lacunes le moins coûteux qui soit.
Étapes
1. Identifier le process concerné
Demande (ou déduis de la conversation):
- Quel process était en cours (chemin ou id;
discover_resourcessi le nom est flou). - À quelle étape le problème est apparu.
2. Cerner l'écart
Fais préciser chacun en une phrase:
- Attendu: ce que le process annonce.
- Observé: ce qui s'est réellement passé (montant faux, donnée périmée, étape impossible…).
3. Consigner
Appelle l'outil report_friction:
process: le chemin du process concernésummary: l'écart en une ligne (ex. «le barème cité n'est plus le bon»)detail: étape, attendu, observé, et toute correction faite à la mainvia:usersi l'utilisateur dicte,assistantsi tu consignes de toi-même
Si l'outil n'est pas disponible sur cet hôte, propose le contenu du fichier
.ai/feedback/<date>_<process>.md (frontmatter process, reported, via, status: open)
en passant par le gate propose → commit.
4. Confirmer la suite
Indique à l'utilisateur où vit la friction (.ai/feedback/) et ce qu'elle déclenche: elle figure
dans la pile Terrain de Studio et chez base doctor tant qu'un humain n'a pas amendé le process et
ne l'a pas marquée résolue.
Ce que tu ne fais jamais dans ce process
- Corriger le process toi-même. La friction est un signal; l'amendement est une décision humaine.
- Modifier une friction existante. Le journal est append-only: un nouveau constat = une nouvelle entrée.
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.
- 12d ago First seen · 68 lines · 43 tokens per session scan A bb67ea9a0313
signaler-une-friction is a skill published in the GitHub repository ai-swiss/base (45 stars, last pushed 8d ago), licensed Apache-2.0. It adds 43 tokens to every session and 739 once invoked, about $0.0002 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.
Other skills, from other repositories
human-review
Open an HTML file, Markdown file, or localhost page in the browser so the user can edit text directly and leave comments on specific parts, then send all edits and comments back to you. Use after writing or updating something the user will read — specs, plans, reports, newsletter drafts, landing pages, slide decks…
wallet-cli
Operate the TypeScript TRON wallet CLI for accounts, transfers, staking, governance, contracts, signing, chain queries, and password input with wallet-cli 4.13.0. Refuse wallet passwords in argv and require the supported stdin channel. For Java REPL requests, refuse that entry and offer the TypeScript one-shot CLI…
compliance
Use when scoping which regulatory frameworks bind a business — SOC 2, ISO 27001, HIPAA, PCI DSS, EU AI Act, DORA, NIS2 — building a control register with owners and evidence, or standing up the cadence that keeps it audit-ready. NOT drafting privacy-policy/ROPA/DPA or ToS text (that is gdpr-privacy, terms-conditions)…
structured-code-review
Performs a structured five-stage code review covering requirements compliance, correctness, code quality, testing, and security/performance. Each stage uses targeted checklists and categorized feedback (Blocker/Major/Minor/Nit) with actionable suggestions and rationale. Use when the user asks for code review, PR…
self-evolve
Make the agent improve with every task — review the run, distill lessons into durable memory, and reinforce what worked. Use at the end of any non-trivial task, or when the user asks the agent to "learn from this".
apply-consequence-clarity
Use when designing behavioral feedback systems — performance management, compliance mechanisms, software quality loops, or habit formation — to ensure consequences are clear, certain, and swift, because certainty and timing determine behavior modification more than magnitude.