Borrowing it
Nothing to install: this file belongs to agentic-lineage/lineage. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/agentic-lineage/lineage/main/.agents/skills/lineage-package-security-guardrails/SKILL.mdgit clone --depth 1 https://github.com/agentic-lineage/lineageWrote 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/agentic-lineage/lineage/lineage-package-security-guardrails)<a href="https://agentmods.dev/skills/agentic-lineage/lineage/lineage-package-security-guardrails"><img src="https://agentmods.dev/badge/skills/agentic-lineage/lineage/lineage-package-security-guardrails/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/agentic-lineage/lineage/lineage-package-security-guardrails"><img src="https://agentmods.dev/badge/skills/agentic-lineage/lineage/lineage-package-security-guardrails.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 | $0.00057 | $0.00447 |
| Opus 5 | $0.00028 | $0.00224 |
| Sonnet 5 | $0.00011 | $0.00089 |
| Haiku 4.5 | $0.00006 | $0.00045 |
Grade A, and why
lineage-package-security-guardrails 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 11d 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 — 44 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Lineage Package Security Guardrails
Lineage packages are portable local environments. A receiver should be able to inspect what a package will do before it changes their workspace.
Threat Model
Assume every package is untrusted until validated. A malicious or careless package may try to:
- include secrets or private local state;
- reference files outside the package;
- write outside the intended workspace;
- smuggle symlinks or path traversal entries;
- hide risky setup actions behind normal activation;
- make provider-specific assumptions look like core behavior.
Safety Rules
- Import and inspect must not execute setup actions.
- Setup and materialization must be explicit, reviewable, permission-gated, and idempotent.
- Never package API keys, auth tokens,
.envvalues, credential stores, provider login state, shell history, or machine-local caches. - Secret checks may report file paths and reasons, but not matched values.
- Prefer templates, schemas, sample CSVs, and placeholder config when private source data should not travel.
- Validate every package-controlled path before reading or writing. Absolute paths and
..traversal are unsafe unless a specific user-provided destination explicitly allows them. - Reject or deliberately handle symlinks. Do not silently follow package symlinks into the receiver's machine.
- Keep capability declarations honest and human-readable. Do not imply enforcement exists until code actually enforces it.
Review Questions
- What exactly can the receiver inspect before enabling or running this package?
- What files will be created, modified, or deleted?
- Can the operation be declined without partial side effects?
- Can the same operation run twice without drift?
- Are source-user data and receiver-local config clearly separated?
- Is provider-specific behavior isolated behind an adapter?
Required Verification
Add tests for unsafe paths, secret-shaped inputs, repeated setup/materialization, and declined permission flows when those surfaces change.
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.
- 11d ago First seen · 44 lines · 57 tokens per session scan A 00f12296a9d0
lineage-package-security-guardrails is a skill published in the GitHub repository agentic-lineage/lineage (10 stars, last pushed yesterday), licensed MIT. It adds 57 tokens to every session and 447 once invoked, about $0.0003 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
fireworks-tech-graph
Create technical diagrams such as software architecture, data flow, flowcharts, sequence diagrams, C4 reviews, cloud deployments, event streams, observability investigations, agent/memory systems, UML, ER, network topology, timelines, and technical concept maps, then export SVG, PNG, focused semantic SVG-to-GIF…
spawn-reviewers
Spawn and collect the reviewer fleet at stage20spawnreviewers. Consumes spawn.json.spec (the authoritative spawn spec from derive-spawn-spec / derive-static-spec), resolves CODEINTELALLOWED, builds per-agent prompts from the per-agent template + role suffixes (Bug Hunter A/B, Unified Auditor, Domain Critics, Impact…
design-inventory
Use to run the Claude Design to ClosedLoop pipeline against the current web-ui. Stage A inventories a design export zip into schema-validated findings (typed design units - screens, regions like nav bars, standalone components like a chat dialog; UX and behavioral changes; Storybook component reuse mapping; token…
artifact-type-tailored-context
Compresses artifacts for judge evaluation. Reads a single raw artifact, applies tiered summarization within a token budget, and returns compacted content with metadata. Isolation via forked context prevents pollution of agent context.
learning-quality
Structured format for capturing high-quality learnings during ClosedLoop runs.
plan-validate
Deterministic plan.json validation via Python script, replacing most plan-validator agent calls. Performs JSON parsing, schema validation, task checkbox regex, required section checks, sync validation, and data extraction. Only semantic consistency checks (storage/query alignment) require the LLM agent. Triggers on…