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 CodeInfinity1/Stram --skill pretextgit clone --depth 1 https://github.com/CodeInfinity1/StramWrote 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/codeinfinity1/stram/pretext)<a href="https://agentmods.dev/skills/codeinfinity1/stram/pretext"><img src="https://agentmods.dev/badge/skills/codeinfinity1/stram/pretext/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/codeinfinity1/stram/pretext"><img src="https://agentmods.dev/badge/skills/codeinfinity1/stram/pretext.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 | $0.00034 | $0.00512 |
| Opus 5.5 | $0.00014 | $0.00205 |
| Sonnet 5.5 | $0.00007 | $0.00102 |
| Haiku 4.5 | $0.00003 | $0.00051 |
Grade A, and why
pretext 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- sketch — 92% identical, 12 lines differ
How it starts
The opening of the file, as written. The whole thing — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Pretext
This is a Stram-native skill. It is authored inside this repository and uses only Stram-owned tools, approval gates, artifacts, and optional dependency records.
When To Use
Use this skill when the user asks for pretext planning, execution, verification, troubleshooting, or artifact creation inside Stram.
Tool Map
tool_searchtool_describecapability_surfacewrite_notenative_security_policytool_output_storepretext_project_preparemedia_storyboard_createmedia_storyboard_inspectsound_spec_creatediagram_artifact_createimage_generatevideo_generatevision_analyzeoptional_dependency_installer
Workflow
- Clarify the user's concrete pretext objective, target environment, credentials already configured, and expected artifact or action.
- Use
tool_searchorcapability_surfaceto find the native Stram tools for the domain before choosing a path. - Run safe inspection/readiness steps first and write bounded notes or artifacts under the workspace or data directory.
- Create native briefs, storyboards, SVG/contact sheets, sound specs, prompts, or local code artifacts before attempting provider generation.
- Use optional dependency requests for domain engines such as ComfyUI, Manim, p5.js, TouchDesigner, Blender, or HyperFrames instead of silently installing them.
- Summarize what ran, what was skipped, what remains blocked, and the exact files or records created.
Safety And Boundaries
- Do not import, execute, or vendor upstream assistant code for this skill.
- Do not store raw secrets; store only environment variable names, secret references, or readiness booleans.
- Use approvals for writes, sends, purchases, desktop control, process launches, provider calls, and destructive operations.
- Respect licensing and avoid claiming a generated asset exists until a local file or provider result is present.
Verification
- Record concrete evidence paths or tool outputs before claiming completion.
- Prefer dry-run or prepared artifacts when credentials, hardware, licenses, or live services are missing.
- If a provider-specific runtime is not configured, report the missing credential or binary by name and stop before live execution.
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 · 53 lines · 34 tokens per session scan A acda46f27957
pretext is a skill published in the GitHub repository CodeInfinity1/Stram (11 stars, last pushed 2mo ago), licensed MIT. It adds 34 tokens to every session and 512 once invoked, about $0.0001 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 2026-09-03.
Other skills, from other repositories
android-pentest
A guide for authorized security testing of Android apps, covering APK inspection, runtime testing, traffic capture, code review, and function hooking. An APK is the installable package used by an Android app.
lighting-report-extract
Check reported lighting quantities and results in supplied simulation PDFs without adding repeated calculation surfaces. Use for scoped luminaire inventories and illuminance results; not simulation or compliance.
authentication-patterns
OAuth 2.0, JWT, SSO, MFA, NextAuth/Clerk/Supabase Auth implementation patterns.
container-debugging
Diagnose reported container build, startup, network, permission and resource failures. Use when an image or Compose service fails; reproduce against the final image/config and avoid data-destroying cleanup as a workaround.
alive:system-upgrade
Upgrade ALIVE to the current version. Handles v1/v2/v3.x source states, multi-surface aware (alive-mcp / Hermes / Codex), retroactive version detection, partial-failure resume, dry-run previews, and rollback inspection.
pr-review
Comprehensive PR review across six dimensions — cost impact, environment drift, ownership gaps, SOC 2 compliance, deprecated API / version hygiene, and rollback feasibility. Each mode inspects the diff and current file state, reports findings with severity, and recommends concrete fixes. Use when preparing a PR for…