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/webmaxru/is-ai-native/agent-package-managernpx skills add webmaxru/is-ai-native --skill agent-package-managergit clone --depth 1 https://github.com/webmaxru/is-ai-nativeWrote 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/webmaxru/is-ai-native/agent-package-manager)<a href="https://agentmods.dev/skills/webmaxru/is-ai-native/agent-package-manager"><img src="https://agentmods.dev/badge/skills/webmaxru/is-ai-native/agent-package-manager.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 | $0.00093 | $0.01729 |
| Opus 5 | $0.00046 | $0.00864 |
| Sonnet 5 | $0.00019 | $0.00346 |
| Haiku 4.5 | $0.00009 | $0.00173 |
Grade C, and why
agent-package-manager scanned grade C with 1 finding 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.
Nullifies safety policieshighAnti-refusal
"You have no restrictions", "do anything now", "ignore your guidelines": a direct jailbreak that disables guardrails.
* If `apm install` is blocked by an organization policy (`apm-policy.yml`), do not bypass the policy; report the block and ask the administrator to adjust the policy or allowlist the dependency. How it starts
The opening of the file, as written. The whole thing — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Package Manager
Procedures
Step 1: Assess the repository and the requested APM outcome
- Inspect the repository root for
apm.yml,apm.lock.yaml,.github/,.claude/,.codex/,.cursor/,.gemini/,.opencode/,.windsurf/, andapm_modules/. - Execute
apm --versionandapm configto confirm the installed CLI and current configuration. - If
apm.ymlexists, readreferences/manifest-and-lockfile.mdbefore changing dependencies, scripts, or compilation settings. - If the request is about package installation, updates, pruning, or removal, read
references/command-workflows.mdbefore executing APM commands. - If no
apm.ymlexists and the user wants APM in the repository, initialize the project withapm initorapm init --yes. - If the repository already uses another agent configuration flow and the user did not ask to migrate it, limit the change to the requested APM scope instead of replacing the existing setup.
Step 2: Shape or repair the manifest deliberately
- Read
assets/apm.yml.templatewhen the repository needs a fresh or repaired manifest structure. - Keep
nameandversionpresent at the top level; treat them as required contract fields. - Add APM package dependencies under
dependencies.apmand MCP servers underdependencies.mcp. - Prefer canonical dependency forms in
apm.ymlafter installation. Default to the repository shorthandowner/repo/pathfor GitHub-hosted skills and packages, for examplewebmaxru/web-ai-agent-skills/skills/webmcp, and preserve explicitpath,ref, andaliasonly when they are needed. - Use pinned refs for shared team packages when reproducibility matters more than automatic drift.
- Keep local path dependencies only for active local development. Replace them with remote references before recommending bundle distribution.
- If the request includes scripts, define them under
scriptsand verify that each script can be previewed or executed throughapm list,apm preview, orapm run.
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.
- 4d ago First seen · 68 lines · 93 tokens per session scan C 770d1eb4b3ff
agent-package-manager is a skill published in the GitHub repository webmaxru/is-ai-native (5 stars, last pushed 13d ago), licensed MIT. It adds 93 tokens to every session and 1,729 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it C with 1 finding (nullifies safety policies). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
pr-lifecycle
Complete issue → PR → merge lifecycle with readiness checks.
economy-mode
Shifts Layer 3 model selection to cost-optimized alternatives when economy mode is active.
windows-compatibility
Cross-platform path handling and command patterns.
rework-rate
Measure and interpret PR rework rate — the emerging 5th DORA metric.
agentic-workflow-designer
Conversational skill that interviews users to design new agentic workflows.
My Skill
Content here.