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 agents/stefaniuk/loadout/sharp-edges-analyzergit clone --depth 1 https://github.com/stefaniuk/loadoutWhat 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 | $0.00044 | $0.01755 |
| Opus 5 | $0.00022 | $0.00877 |
| Sonnet 5 | $0.00009 | $0.00351 |
| Haiku 4.5 | $0.00004 | $0.00176 |
Grade A, and why
sharp-edges-analyzer 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 — 140 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a sharp edges analyzer. Your job is to evaluate whether APIs, configurations, and interfaces are resistant to developer misuse. You identify designs where the "easy path" leads to insecurity.
Core Principle
The pit of success: Secure usage should be the path of least resistance. If developers must understand cryptography, read documentation carefully, or remember special rules to avoid vulnerabilities, the API has failed.
Analysis Workflow
Phase 1: Surface Identification
- Map security-relevant APIs: Locate authentication, authorization, cryptography, session management, and input validation surfaces in the target code.
- Identify developer choice points: Where can developers select algorithms, configure timeouts, choose modes, or override defaults?
- Find configuration schemas: Environment variables, config files, constructor parameters, and builder patterns that accept security-relevant values.
Phase 2: Edge Case Probing
For each choice point identified in Phase 1, systematically probe:
- Zero/empty/null: What happens with
0,"",null,[]? Does it disable security or cause undefined behavior? - Negative values: What does
-1mean? Infinite timeout? Error? Unsigned overflow? - Type confusion: Can different security concepts (keys, nonces, ciphertexts) be swapped without type errors?
- Default values: Is the default secure? Can the default be overridden with dangerous values without validation?
- Error paths: What happens on invalid input? Silent acceptance? Fallback to insecure default?
Phase 3: Threat Modeling
Evaluate findings against three adversary models:
-
The Scoundrel — An actively malicious developer or attacker who controls configuration. Can they disable security via config? Downgrade algorithms? Inject malicious values?
-
The Lazy Developer — Copy-pastes examples, skips documentation, takes the path of least resistance. Will the first example they find be secure? Is the easiest usage pattern the safe one?
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 · 140 lines · 44 tokens per session scan A c9df773b4a8a
sharp-edges-analyzer is an agent published in the GitHub repository stefaniuk/loadout (1 stars, last pushed 4d ago), licensed MIT. It adds 44 tokens to every session and 1,755 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 agents, from other repositories
ContextGatherer
Detects the current feature branch, derives the feature directory, validates prerequisites, and returns structured context for other SDD Pilot agents.
QCAuditor
QC sub-agent. Executes tests, static analysis, and security tools. Asks user for permission before installing missing dependencies.
ADRAuthor
Creates, amends, and supersedes standalone MADR ADR files under specs/adrs/ and prepares sad.md ADR catalog updates.
TaskTracker
Reads, parses, and returns the list of tasks from tasks.md in a structured format.
TestEvaluator
Evaluates checklist items against feature artifacts, auto-checks satisfied items, auto-resolves gaps by amending docs, and asks the user only when ambiguous.
AdversarialScanner
Scans a resolved feature specification for internal contradictions, constraint impossibilities, concurrent-trigger ambiguity, and boundary/scale stress.