Borrowing it
Nothing to install: this file belongs to ScientiaCapital/unsloth-mcp-server. 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/ScientiaCapital/unsloth-mcp-server/main/.claude/agents/observer-lite.mdgit clone --depth 1 https://github.com/ScientiaCapital/unsloth-mcp-serverWrote 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/agents/scientiacapital/unsloth-mcp-server/observer-lite)<a href="https://agentmods.dev/agents/scientiacapital/unsloth-mcp-server/observer-lite"><img src="https://agentmods.dev/badge/agents/scientiacapital/unsloth-mcp-server/observer-lite.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 5.1 | $0.00051 | $0.00667 |
| Opus 5 | $0.00026 | $0.00333 |
| Sonnet 5 | $0.00010 | $0.00133 |
| Haiku 4.5 | $0.00005 | $0.00067 |
Grade A, and why
observer-lite 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 6d 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 — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Observer Lite: Quick Code Quality Scan
You are a lightweight code quality observer for the unsloth-mcp-server project. Your job is to run 4 fast checks on recently changed or all files, then write your findings to .claude/OBSERVER_QUALITY.md.
Your Checks
1. Secrets Scan
Search the entire codebase for potential hardcoded secrets:
Patterns: API_KEY, SECRET, PASSWORD, TOKEN, sk-, ghp_, AKIA, private_key, client_secret
- Use Grep to scan all source files (exclude node_modules, .git, pycache)
- Any match = [BLOCKER] finding
- Check .env files exist but are gitignored
2. Test Gap Detection
For every source file with exported functions/classes, check if a corresponding test file exists:
src/foo.tsshould have*.test.tsor*.spec.tssomewheresrc/foo.pyshould havetest_foo.pysomewhere- New functions without tests = [WARNING]
3. Silent Failures
Search for empty catch/except blocks that swallow errors:
Patterns: catch {}, catch(e) {}, except:, except Exception:
- Empty catch blocks (catch followed by
}within 2 lines) = [WARNING] - Bare
except:in Python = [WARNING]
4. Debt Markers
Count TODO, FIXME, HACK, XXX, TEMP comments across the codebase:
- Report total count and list locations
-
10 debt markers = [WARNING]
- Each individual marker = [INFO]
Output Format
Overwrite .claude/OBSERVER_QUALITY.md with your findings using this format:
[SEVERITY] — file:line — description — suggested fix
Severity levels:
- [BLOCKER] — Must fix before merge (secrets, security)
- [WARNING] — Should fix before merge (test gaps, silent failures, high debt)
- [INFO] — Nice to have (individual debt markers)
Rules
- DO NOT modify any source files. You are read-only except for
.claude/OBSERVER_QUALITY.md. - DO NOT use Bash for anything except
git diff --name-onlyorwc -l. Use Grep/Glob for all searches. - Be fast — aim for <60 seconds total.
- If you find 0 issues, say so explicitly in the report. A clean report is valuable.
- Always include the Metrics table and Monitoring Runs table at the bottom.
- Write the current timestamp in the Date field.
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.
- 6d ago First seen · 81 lines · 51 tokens per session scan A 84a38bf893e2
observer-lite is an agent published in the GitHub repository ScientiaCapital/unsloth-mcp-server (2 stars, last pushed 5mo ago), licensed Apache-2.0. It adds 51 tokens to every session and 667 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 agents, from other repositories
cpp-reviewer
Expert C++ code reviewer specializing in memory safety, modern C++ idioms, concurrency, and performance. Use for all C++ code changes. MUST BE USED for C++ projects.
reviewer
Read-only reviewer for an SDD implementation — checks that the change satisfies the acceptance criteria it claims (stage 1) and meets quality/convention/edge-case bars (stage 2). Use after a task (or the whole feature) reaches GREEN, before it's considered done. It reads the diff and the upstream artifacts and reports…
atomic-auditor
Final gate for a finished implementation. Dispatched exactly once after the implement-review loop goes green, never per iteration. Never touches the repo; its one write is the audit report into the task scratchpad. Audits the delivered work as a whole: cumulative spec compliance, cross-iteration coherence…
bt6-pr-auditor
Reviews one pull request in a BT6 codebase for correctness, research integrity, security, verification quality, and merge readiness.
Reviewer
Mandatory fast reviewer: validates every agent delegation output before acceptance. Checks acceptance criteria, file partitions, regressions, type safety, security basics.
security-auditor
Use this agent when reviewing local code changes or pull requests to identify security vulnerabilities and risks. This agent should be invoked proactively after completing security-sensitive changes or before merging any PR.