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.
npx skills add Ertinox7711/SGRR-AGI-V2 --skill pdf-titregit clone --depth 1 https://github.com/Ertinox7711/SGRR-AGI-V2Wrote 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/ertinox7711/sgrr-agi-v2/pdf-titre)<a href="https://agentmods.dev/skills/ertinox7711/sgrr-agi-v2/pdf-titre"><img src="https://agentmods.dev/badge/skills/ertinox7711/sgrr-agi-v2/pdf-titre/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/ertinox7711/sgrr-agi-v2/pdf-titre"><img src="https://agentmods.dev/badge/skills/ertinox7711/sgrr-agi-v2/pdf-titre.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 | $0.00082 | $0.00548 |
| Opus 5 | $0.00041 | $0.00274 |
| Sonnet 5 | $0.00016 | $0.00110 |
| Haiku 4.5 | $0.00008 | $0.00055 |
Grade A, and why
pdf-titre 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 3d 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
pdf-titre — modifier le titre d'un PDF sans rien casser
Quand l'utiliser
- L'utilisateur demande de changer le titre affiché d'un PDF (barre de titre du lecteur, Explorateur Windows, Adobe, Chrome…).
- On veut modifier ~/Title et le XMP dc:title sans ré-encoder le PDF (aucun risque de casser polices, mise en page, liens, images).
Comment
node ~/.claude/skills/pdf-titre/pdf-titre.mjs "Chemin/vers/fichier.pdf" "Nouveau titre"
- Travaille sur le fichier en place : un update incrémental est simplement ajouté à la fin (mécanisme officiel PDF) — les 100 % d'octets d'origine restent intacts.
- Backup automatique :
<nom>.backup-pdf-titre.pdfà côté du fichier. - Vérif automatique : re-parcours de la chaîne xref comme un lecteur (le titre résolu doit être exactement celui demandé) +
pdftotextsi disponible.
Ce qui est géré
- Fichiers Word 2024 (table classique + section finale vide avec
/Prev, objet-streams, XMP optionnel). - PDF générés par bibliothèques (xref stream
/Type/XRef+ catalogues/Info dans des obj-streams). - Titres ASCII ou accentués (UTF-16BE si nécessaire),
<,&,>échappés dans le XMP.
Ne PAS faire
- Ne jamais ré-écrire un PDF entier (pdftotext n'est pas un éditeur ; exiftool ne modifie pas l'Info ; pad de
/Titlechangeant la longueur sans recalculer la xref corrompt le fichier). - Ne jamais point-à-point écrire les offsets manuellement : toujours recalculer depuis la fin du fichier réel.
- Si le script dit « xref stream non supporté » (vieille version) → mettre à jour le script depuis
.freebuff/pdf-titre.mjsdu projet Formation-SGRR. - PDF chiffrés : non gérés (Erreur).
What ships with it
1 file 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.
- 3d ago First seen · 29 lines · 0 tokens per session scan A 3e35c73fc7ea
pdf-titre is a skill published in the GitHub repository Ertinox7711/SGRR-AGI-V2 (1 stars, last pushed 3d ago), licensed MIT. It adds 82 tokens to every session and 548 once invoked, about $0.0004 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 2026-09-09.
Other skills, from other repositories
ag-5-documentos
Documentacao: Office (PPTX/DOCX/XLSX/PDF), README, API, diagramas, specs, changelog, data dictionary e CSV; executive para decks.
Criar, editar, analisar, merge, split e preencher PDFs. Trigger quando usuario menciona .pdf, quer extrair texto/tabelas, criar relatorio PDF, ou manipular documentos PDF.
ag-revisar-ortografia
Verificador e corretor ortografico para documentos Office, PDF, TXT e MD. Corrige silenciosamente erros de ortografia e acentuacao em PT-BR e EN.
study-guide-gen
This skill converts course materials (PDF, PPTX) into structured Markdown study guides using markitdown.
summarize
Summarize or extract text/transcripts from URLs, podcasts, and local files (great fallback for “transcribe this YouTube/video”).
legal-discovery
Audit e-discovery and litigation document review systems -- data collection pipelines (PST, MBOX, SharePoint, Slack), document processing (OCR via Tesseract/ABBYY, metadata extraction, deduplication), Technology Assisted Review (TAR 1.0/2.0/CAL with recall/precision tracking).