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/voxpelli/vp-claude/intelnpx skills add voxpelli/vp-claude --skill intelgit clone --depth 1 https://github.com/voxpelli/vp-claudeWrote 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/voxpelli/vp-claude/intel)<a href="https://agentmods.dev/skills/voxpelli/vp-claude/intel"><img src="https://agentmods.dev/badge/skills/voxpelli/vp-claude/intel.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 5.1 | $0.00244 | $0.04162 |
| Opus 5 | $0.00122 | $0.02081 |
| Sonnet 5 | $0.00049 | $0.00832 |
| Haiku 4.5 | $0.00024 | $0.00416 |
Grade A, and why
intel 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 6d 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 — 275 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Intelligence
Research a package or a developer/CI tool and synthesize a structured Basic Memory note, then cross-link existing notes. One research lifecycle — detect → check → resolve → enrich → synthesize → write → cross-link — routed per-ecosystem via the table below. The two families (package and tool) share one BM-note lifecycle end to end; Step 3 (enrichment) is the only point where the source roster diverges. Smaller family-specific bits also exist in Arguments normalization, Batch mode, Step 1 freshness, Step 4 observation rules, and Step 6 — but the unifying axis is the shared lifecycle, not the sourcing mechanics.
Supported ecosystems, by family:
- package — npm, Rust crates, Go modules, PHP Composer, Python PyPI, Ruby gems.
- tool — Homebrew formulae/casks, GitHub Actions, Docker images, VSCode extensions, GitHub CLI extensions, Claude Code plugins, skills.sh agent-skill bundles.
Arguments
One or more identifiers, each with an optional <prefix>: (a single call may mix
families — npm:fastify brew:ripgrep — and routes each token by its own prefix).
The prefix alone selects the family and the routing row:
| Prefix | Family | BM dir | Note type | Ecosystem ref | Note template |
|---|---|---|---|---|---|
npm |
package | npm/ |
npm_package |
references/ecosystem-npm.md |
references/note-template-npm.md |
crate |
package | crates/ |
crate_package |
references/ecosystem-crates.md |
references/note-template-crates.md |
go |
package | go/ |
go_module |
references/ecosystem-go.md |
references/note-template-go.md |
composer |
package | composer/ |
composer_package |
references/ecosystem-composer.md |
references/note-template-composer.md |
pypi |
package | pypi/ |
pypi_package |
references/ecosystem-pypi.md |
references/note-template-pypi.md |
gem |
package | gems/ |
ruby_gem |
references/ecosystem-gems.md |
references/note-template-gems.md |
brew |
tool | brew/ |
brew_formula |
references/ecosystem-brew.md |
references/note-template-brew.md |
cask |
tool | casks/ |
brew_cask |
references/ecosystem-cask.md |
references/note-template-cask.md |
action |
tool | actions/ |
github_action |
references/ecosystem-action.md |
references/note-template-action.md |
docker |
tool | docker/ |
docker_image |
references/ecosystem-docker.md |
references/note-template-docker.md |
vscode |
tool | vscode/ |
vscode_extension |
references/ecosystem-vscode.md |
references/note-template-vscode.md |
gh |
tool | gh/ |
gh_extension |
references/ecosystem-gh.md |
references/note-template-gh.md |
plugin |
tool | plugins/ |
claude_plugin |
references/ecosystem-plugin.md |
references/note-template-plugin.md |
skill |
tool | plugins/ |
claude_plugin |
references/ecosystem-skill.md |
references/note-template-plugin.md |
What ships with it
37 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.
- references/cross-link-existing-notes.md 3.5 KB
- references/ecosystem-action.md 2.9 KB
- references/ecosystem-brew.md 19 KB
- references/ecosystem-cask.md 5.0 KB
- references/ecosystem-composer.md 2.0 KB
- references/ecosystem-crates.md 2.7 KB
- references/ecosystem-docker.md 3.1 KB
- references/ecosystem-gems.md 2.0 KB
- references/ecosystem-gh.md 6.8 KB
- references/ecosystem-go.md 2.6 KB
- references/ecosystem-npm.md 4.6 KB
- references/ecosystem-plugin.md 3.1 KB
- references/ecosystem-pypi.md 2.3 KB
- references/ecosystem-skill.md 2.7 KB
- references/ecosystem-vscode.md 6.6 KB
- references/enrichment-package.md 18 KB
- references/enrichment-tool.md 26 KB
- references/forge-fallback.md 6.9 KB
- references/gh-api-fallback.md 13 KB
- references/note-lookup-and-freshness.md 5.6 KB
- references/note-template-action.md 3.0 KB
- references/note-template-brew.md 9.6 KB
- references/note-template-cask.md 6.7 KB
- references/note-template-composer.md 2.8 KB
- references/note-template-crates.md 3.8 KB
- references/note-template-docker.md 3.3 KB
- references/note-template-gems.md 2.9 KB
- references/note-template-gh.md 7.3 KB
- references/note-template-go.md 2.9 KB
- references/note-template-npm.md 3.9 KB
- references/note-template-plugin.md 2.1 KB
- references/note-template-pypi.md 3.9 KB
- references/note-template-vscode.md 4.7 KB
- references/note-write-mechanics.md 11 KB
- references/upgrade-haul-adapter-tool.md 9.7 KB
- references/upgrade-haul.md 16 KB
- references/verify-before-capture.md 3.9 KB
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.
- 6d ago First seen · 275 lines · 244 tokens per session scan A 656904339a3a
intel is a skill published in the GitHub repository voxpelli/vp-claude (3 stars, last pushed 8d ago), licensed MIT. It adds 244 tokens to every session and 4,162 once invoked, about $0.0012 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
harden-memories
Audit the bd remember store and recommend which entries to prune, so each one earns its per-session bd prime injection cost. Read-only: it proposes a triage table plus the exact bd forget / migration commands; you run them. Use when bd remember entries have accumulated, feel stale, redundant, or conflicting, or when…
synergy-tracker
Manage cross-project synergy tracking between sibling projects. Use when the user wants to log a shared pattern, a divergence, an extraction candidate, or something a sibling project has that this one doesn't. Also use when the user wants to promote synergy entries to Basic Memory (workflow 5). NOT for upstream…
upstream-tracker
Manage upstream issue tracking for this project. Use when the user wants to log a bug or friction point in a vendor package or npm dependency, review open upstream items, resolve a tracked issue, run a trend review, generate the upstream observations section of a sprint retrospective, promote upstream observations to…
retrospective
Run a sprint retrospective for this project. Use when the user says 'retrospective', 'retro', 'close out the sprint', 'what went well', 'generate retro', or wants to generate a RETRO-NN.md file. Reads UPSTREAM-.md files, recent git history, and conversation context to pre-populate the retrospective. Do NOT use for…
swarm-wave
Orchestrate multi-agent development sprints with wave-based parallelism. Use when the user wants to plan a swarm sprint, partition work into file-disjoint waves, map file contention across open issues, run a post-wave quality gate with review agents, manage agent backpressure, run a parallel research wave, or…
backlog-groomer
Manage the beads backlog for this project. Use when the user wants to review or triage open issues, reprioritize the backlog, identify obsolete issues to close, investigate a topic to inform future work, create new issues from research findings, or enrich an existing issue with external context. Trigger phrases…