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 skills add iampantherr/SecureContext --skill developer-anti-patterns-to-avoidgit clone --depth 1 https://github.com/iampantherr/SecureContextWrote 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/skills/iampantherr/securecontext/developer-anti-patterns-to-avoid)<a href="https://agentmods.dev/skills/iampantherr/securecontext/developer-anti-patterns-to-avoid"><img src="https://agentmods.dev/badge/skills/iampantherr/securecontext/developer-anti-patterns-to-avoid/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/skills/iampantherr/securecontext/developer-anti-patterns-to-avoid"><img src="https://agentmods.dev/badge/skills/iampantherr/securecontext/developer-anti-patterns-to-avoid.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 | $0.00026 | $0.00624 |
| Opus 5 | $0.00013 | $0.00312 |
| Sonnet 5 | $0.00005 | $0.00125 |
| Haiku 4.5 | $0.00003 | $0.00062 |
Grade A, and why
developer-anti-patterns-to-avoid 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 yesterday.
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.
What it actually says
ANTI-PATTERNS TO AVOID
(Extracted from roles.json deepPrompt for the developer role during the v0.19.0 role/skill split. Original content preserved verbatim. Edit freely; the mutator will propose improvements based on skill_runs telemetry once this skill is invoked by an agent.)
- Cargo-cult architecture: Copying Netflix's microservice architecture because it worked for Netflix, without Netflix's scale, team size, or traffic patterns.
- Resume-driven development: Choosing technologies because they're interesting to learn, not because they're the right fit.
- Optimistic merging: Merging PRs without understanding what they do. "LGTM" without reading is not code review.
- Shotgun debugging: Making random changes and hoping the bug goes away. Each change must test a specific hypothesis.
- God objects: Classes or modules that know too much and do too much. If it imports more than 10 other modules, it has boundary problems.
- Swallowed exceptions: catch (e) {} or catch (e) { return null; }. Errors must be either handled or propagated, never silently discarded.
- Magic numbers and strings: Literals in logic with no explanation. Name your constants and explain their origin.
- Synchronous blocking in async contexts: CPU-intensive work on the event loop thread. Long-running synchronous operations in async code starve the runtime.
- Over-engineering for scale you don't have: Message queues for 100 daily users. Kubernetes for a three-endpoint API. Complexity has carrying cost whether or not it buys you anything.
- Test theater: 95% code coverage on trivially correct code, zero coverage on complex business logic. Coverage is a floor, not a goal.
- Dependency injection frameworks for dependency injection problems: If you need a DI framework to manage your dependencies, you have too many dependencies. Simplify the design.
- Distributed monolith: Microservices that share a database, require simultaneous deployment, or fail together. You've paid the cost of distributed systems without gaining the benefits.
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.
- yesterday First seen · 39 lines · 26 tokens per session scan A 40012bf813b6
developer-anti-patterns-to-avoid is a skill published in the GitHub repository iampantherr/SecureContext (8 stars, last pushed 2d ago), licensed MIT. It adds 26 tokens to every session and 624 once invoked, about $0.0001 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 2026-09-08.
Other skills, from other repositories
audit
Project health audit and health check — architecture, performance, tests, dependencies, code quality. Use when assessing overall project health, before releases, or after refactors.
kn-doc
Use when working with Knowns documentation - viewing, searching, creating, or updating docs.
issue-analyze
GitHub Issue and PR review thread deep analysis with Codex blind verdict. Use when: analyzing issue root cause, classifying problems, investigation planning, triaging PR review comments for actionability. Not for: fixing bugs (use bug-fix), code exploration (use code-explore). Output: classified analysis + verdict…
skeptical-triage
Reusable 3-round self-challenge + arbiter pattern for filtering false positives from findings/verdicts. Use when the cost of a false-positive gate block exceeds the cost of 4 extra LLM turns.
anti-patterns
Catalogue of known SDLC anti-patterns that greatcto agents must actively reject when reviewing architecture, plans, code, or post-mortems. Used by architect (pre-impl), pm (planning), senior-dev (impl), l3-support (post-incident).
roslyn-query
Query .NET/C# codebases using Roslyn AST analysis via dotnet run file. Use for tracing data flow, auditing API usage, finding pattern violations, or ad-hoc codebase queries.