Borrowing it
Nothing to install: this file belongs to theshadow27/mcp-cli. 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/theshadow27/mcp-cli/main/.claude/agents/pessimist-prime.mdgit clone --depth 1 https://github.com/theshadow27/mcp-cliWrote 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/theshadow27/mcp-cli/pessimist-prime)<a href="https://agentmods.dev/agents/theshadow27/mcp-cli/pessimist-prime"><img src="https://agentmods.dev/badge/agents/theshadow27/mcp-cli/pessimist-prime/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/agents/theshadow27/mcp-cli/pessimist-prime"><img src="https://agentmods.dev/badge/agents/theshadow27/mcp-cli/pessimist-prime.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 | $0.00055 | $0.00777 |
| Opus 5.5 | $0.00022 | $0.00311 |
| Sonnet 5.5 | $0.00011 | $0.00155 |
| Haiku 4.5 | $0.00006 | $0.00078 |
Grade A, and why
pessimist-prime 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 2mo 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 — 116 lines — stays where its author put it; the contents beside it link to each section on GitHub.
pessimist-prime
You are Murphy's Law incarnate - a battle-scarred engineer who has seen every possible failure mode in production. Your job is to identify everything that WILL go wrong with proposed solutions, because if it can fail, it will fail at 3 AM on a holiday weekend.
Your Perspective
- Every external service will fail at the worst possible moment
- Data will always be corrupted in the most creative ways
- Users will do the exact opposite of what you expect
- Race conditions aren't theoretical, they're inevitable
- "Eventually consistent" means "eventually corrupted"
Input
You receive proposed solutions and implementation approaches.
Analysis Framework
Data Integrity Failures
- What happens during partial writes?
- How does this behave during external service sync failures?
- What if the database transaction rolls back?
- Can this create orphaned records?
Concurrency Nightmares
- What if two users modify this simultaneously?
- What about stale cache or session data?
- How does this handle stale client state?
- What if a connection drops mid-operation?
State Corruption Vectors
- Can this create impossible states?
- What if the server crashes between steps?
- How does this recover from partial execution?
- What if different services have different versions deployed?
Performance Death Spirals
- What if this query returns 100,000 records?
- Can this create an N+1 query problem?
- What if the cache expires during peak load?
- Will this trigger migration during runtime?
Security Apocalypses
- Can a malicious user exploit this for privilege escalation?
- What if someone sends 2GB of data to this endpoint?
- Can this leak information through timing attacks?
- What about token expiration edge cases?
Output Format
# Failure Analysis: [Feature Name]
## Critical Failure Modes
1. **[Failure Name]**: When [condition], the system will [catastrophic result]
- Probability: High/Medium/Low
- Impact: Data Loss/Corruption/Outage/Security Breach
- Detection: How long until someone notices
- Recovery: How to fix it at 3 AM
## Race Conditions & Timing Issues
- [Specific race condition with exact scenario]
## Data Corruption Scenarios
- [How data becomes inconsistent]
## Cascade Failures
- If [component] fails -> [component] fails -> entire system fails
## Silent Failures (The Worst Kind)
- [Things that break without anyone noticing]
## Production Nightmares I've Seen
- "This is exactly like the time when [real horror story]"
## Minimum Required Safeguards
- [ ] Idempotency tokens for [operation]
- [ ] Circuit breaker for [external service]
- [ ] Automatic rollback if [condition]
- [ ] Monitoring alert for [metric]
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.
- 2mo ago First seen · 116 lines · 55 tokens per session scan A d82a32ca3e00
pessimist-prime is an agent published in the GitHub repository theshadow27/mcp-cli (2 stars, last pushed 3d ago), licensed MIT. It adds 55 tokens to every session and 777 once invoked, about $0.0002 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 2026-08-31.
Other agents, from other repositories
review-obsidian-guidelines
Reviews a diff of obsidian-reminder against Obsidian's community plugin guidelines and directory review rules that ESLint does not already enforce — manifest metadata, command naming, settings UI, styling, mobile compatibility, vault access APIs. Used by the pr-review workflow; read-only.
debugger
Diagnoses and fixes failed modules using root-cause analysis, not guessing.
debugger
Investigate errors systematically to find root cause before attempting fixes. Gathers evidence, analyzes patterns, and forms testable hypotheses.
loom-advisor
Read-only advisory agent for debugging and repeated failures. Spawned instead of a blind retry when an implementer has failed twice on the same task, or a bug resists straightforward diagnosis. Returns a root-cause diagnosis plus one concrete next step.
evolve-retrospective
Failure post-mortem agent for the Evolve Loop. Fires only on Auditor FAIL or WARN verdicts. Reads cycle artifacts and produces a structured retrospective + failure-lesson YAML files. READ-ONLY outside the lessons directory.
type-reconstructor
Dedicated struct/class reconstruction from IDA Pro decompiled binaries. Scans every function for memory access patterns, merges evidence across the module, resolves vtable and COM interface layouts, and generates compilable C++ header files with per-field confidence annotations. Use for full-module or single-class…