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 blessonism/openclaw-skills --skill dependency-trackergit clone --depth 1 https://github.com/blessonism/openclaw-skillsWrote 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/blessonism/openclaw-skills/dependency-tracker)<a href="https://agentmods.dev/skills/blessonism/openclaw-skills/dependency-tracker"><img src="https://agentmods.dev/badge/skills/blessonism/openclaw-skills/dependency-tracker/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/blessonism/openclaw-skills/dependency-tracker"><img src="https://agentmods.dev/badge/skills/blessonism/openclaw-skills/dependency-tracker.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 | $0.00098 | $0.00693 |
| Opus 5.5 | $0.00039 | $0.00277 |
| Sonnet 5.5 | $0.00020 | $0.00139 |
| Haiku 4.5 | $0.00010 | $0.00069 |
Grade A, and why
dependency-tracker 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.
How it starts
The opening of the file, as written. The whole thing — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Dependency Tracker
Track version drift across all OpenClaw dependencies. Detect updates, generate reports, notify Boss.
Quick Start
# 1. Scan — build/refresh the local manifest
python3 scripts/scan.py
# 2. Check — compare local vs remote versions
python3 scripts/check.py
# 3. Report — generate human-readable Markdown report
python3 scripts/report.py
All scripts are in the skill directory: ~/.openclaw/workspace/skills/dependency-tracker/scripts/
What It Tracks
| Category | Source | Detection Method |
|---|---|---|
| Managed skills (GitHub) | .skill-lock.json |
GitHub Contents API (git hash compare) |
| Managed skills (ClewHub) | _meta.json |
ClewHub API (version compare) |
| Bundled skills | /app/skills/ |
Tied to OpenClaw version |
| Workspace skills | workspace/skills/ |
Local git (self-managed) |
| OpenClaw version | npm registry + GitHub | npm view / GitHub Releases API |
| npm dependencies | /app/node_modules/ |
npm outdated |
| pip packages | system Python | pip3 list --outdated |
| CLI tools | PATH | Version commands |
Workflow
On-Demand Check
When user asks to check dependencies:
- Run
scan.pyto refresh the manifest - Run
check.pyto compare against remote sources - Run
report.pyto generate the report - Send report summary to user (Telegram)
- If unknown-source skills found, notify Boss
Scheduled Check (Cron)
Set up a weekly cron job:
- Run all three scripts in sequence
- Push report summary to Telegram
- Only notify if updates are found or errors occur
Data Files
All runtime data lives in data/ (gitignored from backup):
data/
├── manifest.json # Full dependency inventory
├── check-results.json # Latest check results
└── reports/
└── YYYY-MM-DD-report.md # Generated reports
Key Design Decisions
- No auto-update: Only detect and report. User decides when to update.
- GitHub hash comparison: Uses
git hash-objectlocally vs GitHub Contents API SHA — exact match, no false positives. - Lock file as source of truth:
.skill-lock.json(OpenClaw's managed skill registry) provides repo URLs and install metadata. - Changelog extraction: For GitHub skills with updates, fetches recent commits for context.
- Unknown source notification: Skills without traceable source are flagged and reported to Boss.
What ships with it
4 files 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.
- 1mo ago First seen · 81 lines · 98 tokens per session scan A 4e1e48c4fbe0
dependency-tracker is a skill published in the GitHub repository blessonism/openclaw-skills (55 stars, last pushed 7mo ago), licensed MIT. It adds 98 tokens to every session and 693 once invoked, about $0.0004 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.
Other skills, from other repositories
web-search
A web-search and information-retrieval skill for finding pages, current information, and news online.
foldseek
Structure similarity search with Foldseek. Use this skill when: (1) Finding similar structures in PDB/AFDB databases, (2) Structural homology search, (3) Database queries by 3D structure, (4) Finding remote homologs not detected by sequence, (5) Clustering structures by similarity. For sequence similarity, use uniprot…
pilot-archive
Index and search historical data exchanges, messages, and file transfers over Pilot Protocol. Use this skill when: 1. You need to search through past messages and file transfers 2. You want to maintain searchable history of all agent communications 3. You need to audit or analyze historical data exchange patterns Do…
pilot-discover
Advanced agent discovery by tags and status. Use this skill when: 1. Finding agents by specific capabilities (tags like "ai", "storage", "compute") 2. Looking up detailed agent information and metadata 3. Filtering connected peers by tag substring Do NOT use this skill when: - You need to establish trust (use…
web-search
Search the web using MiniMax websearch tool for real-time information, news, and facts.
baidu-api-search
A search tool for Chinese-language requests that uses Baidu Encyclopedia and Baidu AI Search APIs. It keeps the original results, removes duplicates, and packages the findings for research.