tma1
tma1 is a Context window & token budget skill for AI agents, published by tma1-ai in the tma1 repository on GitHub. Skillspace rates tma1 F (15/100) and the safety scan rated it unsafe; the rating is based on static analysis only.
Unsafe. This skill has patterns associated with malicious or dangerous behaviour. We do not recommend running it.
Local-first LLM agent observability that closes the loop: records agent work on the user's machine, then feeds the useful parts back into the next turn via hooks, MCP tools, and anomaly detection. Use when users say: - "install tma1" - "upgrade tma1" - "update tma1" - "setup observability" - "monitor my agent" - "how much am I spending on tokens" - "what has my agent been doing" - "local observability" - "I don't want to send data to the cloud" - "track token usage" - "agent metrics" - "agent telemetry" - "what is my agent executing" - "agent security audit" - "prompt injection risk" - "close the agent loop" - "inject session context" - "call tma1 MCP tools" - "list anomalies" - "show me detected anomalies" - "what did Codex / OpenClaw / Copilot do on this project" - "/tma1-peer" - "block stop on anomalies" - "what's the build status"
- Grade
- F
- Quality
- 15 / 100
- Safety
- Unsafe
- GitHub stars
- 109
Unproven: rated by static analysis only, not yet compared head-to-head.
Our two independent classifiers differ on this skill's category, so treat the placement as provisional.
This rating describes the version of the repository we crawled; it may have changed since.
Our review
- Architecture
- 75 / 100
- Maturity
- Structured: ships references or scripts
- Security scan
- Critical-risk patterns
- License
- Apache-2.0
- Adoption
- Adopted by 0 other repositories, in 0 collections
What the scanner flagged
- pipe remote script to shell
- mentions secrets in text
Not checked yet
- Not judged on the rubric yet (not a contender in its category)
- No blind task eval yet
- Scope (portable / vendor / repo-internal) not assessed; only the top of each category is read for scope
- Sibling files (scripts, references) not fetched; security scan covers SKILL.md only
Skillspace indexes and rates this skill; it does not host or endorse it. Run third-party skills at your own risk.