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/codeinfinity1/stram/agent-self-assessmentnpx skills add CodeInfinity1/Stram --skill agent-self-assessmentgit clone --depth 1 https://github.com/CodeInfinity1/StramWhat 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 | $0.00048 | $0.00664 |
| Opus 5 | $0.00024 | $0.00332 |
| Sonnet 5 | $0.00010 | $0.00133 |
| Haiku 4.5 | $0.00005 | $0.00066 |
Grade A, and why
agent-self-assessment 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 2d 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 — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Self Assessment
Purpose
Create an explicit readiness check before the assistant commits to complex action. This skill combines external reference agent audit and self-assessment ideas with Stram capability, tool, policy, and cognition surfaces.
When To Use
Use for high-impact tasks, broad architecture changes, long autonomous runs, external integrations, multi-agent work, or when the assistant is unsure whether it has enough tools and context.
Inputs And Evidence
- Capability surface and tool descriptions.
- Current workspace state and relevant files.
- Model provider readiness.
- Safety policy and approval requirements.
- Known blockers, memory, and environment constraints.
Tool Map
capability_surfacetool_searchtool_describecognitive_self_reviewcognitive_environment_statussystem_statusplugin_catalogchannel_catalog
Workflow
- Clarify the objective and expected end state.
- Inspect capability surface and relevant tool schemas.
- Identify missing credentials, missing tools, policy gates, and high-risk actions.
- Decide whether to proceed, narrow scope, ask for input, or run a safer dry run.
- Define verification evidence before execution.
- Reassess after failures or surprising tool output.
Safety And Boundaries
- Do not use assessment as a substitute for doing safe, obvious work.
- Do not downplay risks when tools can affect external systems.
- If a model/provider is unavailable, stop or use explicit tool commands only; do not invent deterministic intent handling.
Safety And Approval
- Treat self-assessment as advisory evidence, not permission to bypass approval gates.
- If the assessment identifies external-visible, destructive, privileged, or privacy-sensitive actions, require the relevant tool approval before execution.
- Do not downgrade risk because a task is familiar; use current tool schemas, provider status, credentials, and workspace state.
- Report model-unavailable or tool-unavailable states honestly instead of substituting brittle keyword rules.
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.
- 2d ago First seen · 80 lines · 48 tokens per session scan A b5dce37429ef
agent-self-assessment is a skill published in the GitHub repository CodeInfinity1/Stram (10 stars, last pushed 22d ago), licensed MIT. It adds 48 tokens to every session and 664 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 2026-08-31.
Other skills, from other repositories
opencli-sitemap-author
Use when creating or maintaining OpenCLI site sitemaps: agent-facing navigation, page-state, action, workflow, API-reference, pitfall, and fallback knowledge for a website. Use after browser exploration discovers durable site context, when a sitemap is stale, or when promoting local site knowledge into the repo.
golden-rss
Use when testing the rss golden build.
omh-code-review
This is a Hermes-native code-review workflow skill.
redteam-web-detail-pack
Routing and boundary guidance for authorized general web application security testing. Use as a web testing router when the attack surface should be dispatched to more specific web vulnerability skills.
android-pentest
安卓应用渗透测试 — APK分析、Hook、自动化测试、运行态驱动、签名恢复、抓包分析.
studio
Architecture Studio control plane — initialize or inspect a studio workspace, create and register projects, or route an architecture/AEC task to the right agent or skill. Use when the user runs /as:studio, asks to set up or open their studio, manage its projects, or describes a task without naming a skill.