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 commands/sgaunet/claude-plugins/upd-project-descriptiongit clone --depth 1 https://github.com/sgaunet/claude-pluginsWrote 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/commands/sgaunet/claude-plugins/upd-project-description)<a href="https://agentmods.dev/commands/sgaunet/claude-plugins/upd-project-description"><img src="https://agentmods.dev/badge/commands/sgaunet/claude-plugins/upd-project-description.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 | $0.00022 | $0.01170 |
| Opus 5 | $0.00011 | $0.00585 |
| Sonnet 5 | $0.00004 | $0.00234 |
| Haiku 4.5 | $0.00002 | $0.00117 |
Grade B, and why
upd-project-description scanned grade B with 2 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 4d 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.
Sends data to an external URLmediumData exfiltration
A POST to an outside endpoint may be telemetry or may be exfiltration; either way the mod talks to somewhere, and you should know where.
`curl -X PATCH -H "Authorization: token <TOKEN>" -H "Content-Type: application/json" -d '{"description":"<description>"}' <api_base>/repos/<owner>/<repo>` Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
allowed-tools: Read, Skill, Bash(gh:*), Bash(glab:*), Bash(fgj:*), Bash(curl:*) How it starts
The opening of the file, as written. The whole thing — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Update Project Description Command
Update the description and topics of the current project. This command automatically detects whether the repository is hosted on GitHub, GitLab, or Forgejo and uses the appropriate CLI (or REST API for Forgejo) to update the project metadata (description and topics/tags).
Process
-
Detect Repository Host: Use the
detect-repo-hostskill to identify the hosting service (GitHub, GitLab, or Forgejo) and extract owner/repo details. -
Analyze README: Use a Haiku agent to analyze the README.md file:
- Extract concise project description (first 1-2 paragraphs, max 200 chars)
- Identify relevant topics/tags from content (technologies, frameworks, keywords)
- Return:
{description: "...", topics: ["topic1", "topic2", ...]}
-
Launch 2 parallel Haiku agents to update project metadata concurrently:
Agent #1: Update Project Description
-
GitHub:
gh repo edit --description "<description>" -
GitLab:
glab repo edit --description "<description>" -
Forgejo:
fgjhas norepo editsubcommand — call the Forgejo REST API withcurl, using the token fromfgj auth token:curl -X PATCH -H "Authorization: token <TOKEN>" -H "Content-Type: application/json" -d '{"description":"<description>"}' <api_base>/repos/<owner>/<repo><api_base>is the field returned by thedetect-repo-hostskill (e.g.https://git.sylvlab.fr/api/v1). Never hardcode a host. -
Return: success/failure status
Agent #2: Update Project Topics/Tags
- GitHub:
gh repo edit --add-topic "<topic>"(one per topic) - GitLab:
glab repo edit --tag "<topic>"(one per topic) - Forgejo:
fgjhas norepo editsubcommand — call the Forgejo REST API withcurl, using the token fromfgj auth token(sets the full topic list in one call):curl -X PUT -H "Authorization: token <TOKEN>" -H "Content-Type: application/json" -d '{"topics":["<topic1>","<topic2>"]}' <api_base>/repos/<owner>/<repo>/topics - Return: success/failure status
-
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.
- 4d ago First seen · 73 lines · 22 tokens per session scan B 831d1d3d54c7
upd-project-description is a command published in the GitHub repository sgaunet/claude-plugins (16 stars, last pushed 2d ago), licensed MIT. It adds 22 tokens to every session and 1,170 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it B with 2 findings (sends data to an external url, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other commands, from other repositories
security-audit-static
Static security audit of AI-built code — map trust boundaries, cross-reference documented intent, self-refute every finding, and report only evidence-backed risks.
performance-audit-static
Static performance audit of AI-built code — find N+1 queries and request waterfalls, over-fetching, missing indexes, and caching opportunities, ranked by effort and impact.
document-app
Reverse-engineer an AI-built codebase into the system documents reviewers and auditors need — a core set (architecture, flows, permissions, variables) plus conditional docs (emails, cron, SEO, automation) when they apply.
plan-okrs
Brainstorm team-level OKRs aligned with company objectives — qualitative objectives with measurable key results.
write-stories
Break a feature into backlog items — user stories, job stories, or WWA format with acceptance criteria.
battlecard
Create a sales-ready competitive battlecard — positioning, feature comparison, objection handling, and win strategies.