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 agentmods add skills/topness-msft/crowdhum-plugin/session-recapnpx skills add topness-msft/crowdhum-plugin --skill session-recapgit clone --depth 1 https://github.com/topness-msft/crowdhum-pluginWrote 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/topness-msft/crowdhum-plugin/session-recap)<a href="https://agentmods.dev/skills/topness-msft/crowdhum-plugin/session-recap"><img src="https://agentmods.dev/badge/skills/topness-msft/crowdhum-plugin/session-recap.svg" alt="Measured on agentmods" 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 | $0.00117 | $0.01057 |
| Opus 5 | $0.00059 | $0.00528 |
| Sonnet 5 | $0.00023 | $0.00211 |
| Haiku 4.5 | $0.00012 | $0.00106 |
Grade A, and why
session-recap 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.
The source is not reproduced here
No licence file
A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.
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 · 104 lines · 117 tokens per session scan A 69a7a27cb884
session-recap is a skill published in the GitHub repository topness-msft/crowdhum-plugin (0 stars, last pushed 1mo ago), with no licence file. It adds 117 tokens to every session and 1,057 once invoked, about $0.0006 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 2026-08-31.
Other skills, from other repositories
prompt-architect
Build a high-quality, structured prompt for any task using Anthropic's 10-block prompting framework from the "Prompting 101" workshop (Code w/ Claude, May 2025). Primary trigger is the slash command /prompt-architect. Also triggers when the user asks to "write a prompt", "build a prompt", "improve this prompt", "make…
persona-creation
Créer des personas synthétiques vivants et psychologiquement crédibles à partir de données réelles (transcriptions AI Notetaker, ICP, notes clients). Utiliser ce skill dès que l'utilisateur tape /Creation, demande de "créer un persona", "générer un profil client", "construire un persona synthétique", ou mentionne…
persona-optimisation
Affiner, corriger ou enrichir un persona synthétique existant sans repartir de zéro. Utiliser ce skill dès que l'utilisateur tape /Optimisation, dit "ce persona sonne faux", "affine [prénom]", "il est trop lisse", "ajoute ce biais", "corrige cette objection", "le persona ne correspond plus à ma réalité", ou signale un…
persona-panel
Réunir plusieurs personas synthétiques validés et les interroger simultanément. Utiliser ce skill dès que l'utilisateur tape /Panel, dit "réunis mes personas", "je veux que plusieurs personas répondent à la même question", "fais débattre mes personas", "salle de réunion virtuelle", ou veut comparer les réactions de…
persona-context
Alimenter le plugin avec de nouvelles données pour mettre à jour les personas existants ou enrichir la base de connaissance avant une création. Utiliser ce skill dès que l'utilisateur tape /Context, dit "j'ai de nouveaux calls", "voici de nouvelles transcriptions", "j'ai un rapport d'étude à intégrer", "mon marché a…
persona-discussion
Activer un persona synthétique validé et engager une simulation conversationnelle avec lui. Utiliser ce skill dès que l'utilisateur tape /Discussion, dit "je veux parler à [prénom]", "simule une conversation avec mon persona", "teste mon pitch avec [prénom]", "joue le rôle de [prénom]", ou demande à Claude d'incarner…