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/plamentsv/plamen/dependency-audit-nodeclientnpx skills add PlamenTSV/plamen --skill dependency-audit-nodeclientgit clone --depth 1 https://github.com/PlamenTSV/plamenWhat 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 | $0.00033 | $0.01926 |
| Opus 5 | $0.00016 | $0.00963 |
| Sonnet 5 | $0.00007 | $0.00385 |
| Haiku 4.5 | $0.00003 | $0.00193 |
Grade A, and why
dependency-audit-nodeclient 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.
How it starts
The opening of the file, as written. The whole thing — 142 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Injectable Skill: Node Client Dependency Audit
L1 trigger:
L1_PATTERN=true— always runs Inject Into: Recon + any breadth agent Finding prefix:[DEP-N]Status: v0.1 draft, Round 4 exemplars pending
When This Skill Activates
Always active in L1 mode. Extends Plamen's existing dependency-audit skill with Go/Rust-specific checks relevant to node clients.
1. Go Module Audit
1a. Version check
- Read
go.mod— identify everyrequireline - Check against Go vulnerability database:
govulncheck ./...(ships with Go 1.18+) - Check against OSV: https://osv.dev/
- Check against GitHub advisories for each dep
1b. Replace directive audit
replacedirectives ingo.modcan redirect a dep to a fork or local path- Every
replaceis a trust statement: the audit must identify what's being replaced with what, and whether the replacement is authentic - Fork audits: the target likely has
replacepointing to the parent client (e.g.,replace github.com/ethereum/go-ethereum => github.com/ethereum-optimism/op-geth v1.x.y) - Flag every
replacewith an explicit note in the finding
Tag: [GO-REPLACE:{original}:{replacement}:{trust-note}]
1c. vendor/ directory
- If the target uses
vendor/, check if vendored code matches upstream. Modified vendored deps are a red flag. - Run
go mod verifyif possible to check checksums
Tag: [GO-VENDOR-DIFF:{module}]
1d. Indirect dependency bloat
- Excessive transitive deps increase the attack surface
- For each
// indirectline, ask: is the intermediate dep actually used?
2. Rust Cargo Audit
2a. Version check
cargo audit(requires the cargo-audit tool; install withcargo install cargo-audit)- Reads
Cargo.lockagainst the RustSec advisory database (https://rustsec.org/) cargo denyfor richer policy (denylist, license, trust)
2b. Patch directive audit
[patch.crates-io]and[patch."https://..."]blocks inCargo.tomland workspace root- Same trust concern as Go
replace: patches redirect deps - Fork audits: likely patches pointing to parent client
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 · 142 lines · 33 tokens per session scan A 2237c1a69a18
dependency-audit-nodeclient is a skill published in the GitHub repository PlamenTSV/plamen (281 stars, last pushed 1mo ago), licensed MIT. It adds 33 tokens to every session and 1,926 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
go-rust-reverse
Use for reverse engineering stripped Go and Rust binaries including runtime recognition, pclntab/moduel data recovery, panic strings, and idiomatic decompilation recovery.
go-development
Go development workflow including verification commands and self-review checklist. Use when modifying Go code in internal/, pkg/, or cmd/ directories.
port-from-go
Port Go into Rust — goroutines and channels onto tasks and async, interfaces onto traits, error values onto Result, and the value-semantics traps (zero values, integer wraparound, slice aliasing, nil). Use when porting, rewriting, or migrating Go, Golang, a Go service, or a Go CLI into Rust, when replacing a Go…
go-rust-systems
Go and Rust systems programming best practices for performance-critical, concurrent, and safe applications. Covers error handling, ownership/borrowing (Rust), context and goroutines (Go), testing patterns, and production deployment. Use when working with .go, .rs files, Cargo.toml, go.mod, or when asking about Go or…
go-rust-reverse
Use for reverse engineering stripped Go and Rust binaries including runtime recognition, pclntab/moduel data recovery, panic strings, and idiomatic decompilation recovery.
Capsule Development
Build, test, package, install, and debug a current Unicity AOS capsule.