# Redtropig > Open-source publisher. Listings imported from github.com/Redtropig — credited to the original author with their license. - **Listings:** 14 - **Total installs:** 0 - **Profile:** https://agentstack.voostack.com/s/redtropig - **Website:** https://github.com/Redtropig ## Published listings - [Anti Hallucination Gates](https://agentstack.voostack.com/l/skill-redtropig-harness-anchor-anti-hallucination-gates) — Skill · Free · security-reviewed — `agentstack add skill-redtropig-harness-anchor-anti-hallucination-gates` Use before claiming done/fixed/passing — or before asserting something is absent: not installed, not available, no such function, couldn't find it. Default-FAIL runs both ways — every claim needs an evidence path. A negative claim must carry its search scope and observation date; state calibrated uncertainty when evidence is missing. - [Cpp Build Systems](https://agentstack.voostack.com/l/skill-redtropig-harness-anchor-cpp-build-systems) — Skill · Free · security-reviewed — `agentstack add skill-redtropig-harness-anchor-cpp-build-systems` Use in C/C++ projects for build configure/errors, compile_commands.json generation, or selecting CMake/Meson/Make/Bazel commands. - [Cpp Formatting](https://agentstack.voostack.com/l/skill-redtropig-harness-anchor-cpp-formatting) — Skill · Free · security-reviewed — `agentstack add skill-redtropig-harness-anchor-cpp-formatting` Use in C/C++ projects for clang-format. Changed-lines-only; never reformat unchanged code mid-feature. .clang-format from root or LLVM baseline. - [Docs Lookup](https://agentstack.voostack.com/l/skill-redtropig-harness-anchor-docs-lookup) — Skill · Free · security-reviewed — `agentstack add skill-redtropig-harness-anchor-docs-lookup` Use when looking up unfamiliar tools, APIs, errors, library behavior. Context7 → WebSearch → calibrated uncertainty fallback chain. Don't guess. - [Project Indexing](https://agentstack.voostack.com/l/skill-redtropig-harness-anchor-project-indexing) — Skill · Free · security-reviewed — `agentstack add skill-redtropig-harness-anchor-project-indexing` Use when locating files or understanding structure. Consults PROJECT-TOC.md (one-line index per file). Staleness via git commit anchor. - [Context Budget Discipline](https://agentstack.voostack.com/l/skill-redtropig-harness-anchor-context-budget-discipline) — Skill · Free · security-reviewed — `agentstack add skill-redtropig-harness-anchor-context-budget-discipline` Use when sessions run long, adding subagents, fetching large files, or planning context-heavy work. SELECT/WRITE/COMPRESS/ISOLATE discipline. - [Using Harness Anchor](https://agentstack.voostack.com/l/skill-redtropig-harness-anchor-using-harness-anchor) — Skill · Free · security-reviewed — `agentstack add skill-redtropig-harness-anchor-using-harness-anchor` Use whenever working in a project. Establishes state/scope/verification discipline. Auto-loaded at session start. Complements superpowers. - [Test Coverage Design](https://agentstack.voostack.com/l/skill-redtropig-harness-anchor-test-coverage-design) — Skill · Free · security-reviewed — `agentstack add skill-redtropig-harness-anchor-test-coverage-design` Use when deciding what to test, reviewing whether a feature is adequately covered before calling it done, or when tests pass but you're unsure they exercise the real risks. Derives coverage obligations from code + spec, finds gaps (including paths outside the test runner's scope), and designs a minimal, edge-case-first test set. Dispatches the coverage-analyst subagent. Generic (language-agnostic… - [Capturing Golden Rules](https://agentstack.voostack.com/l/skill-redtropig-harness-anchor-capturing-golden-rules) — Skill · Free · security-reviewed — `agentstack add skill-redtropig-harness-anchor-capturing-golden-rules` Use when the same mistake or bad pattern recurs, when a code-review comment is really a convention worth enforcing, or when you catch AI-generated drift/slop and want it to never happen again. Encodes the lesson as a durable rule in golden-rules.md — the feedback-flywheel / harness-layer-learning ratchet — instead of a one-off fix. Generic (language-agnostic). - [Init Verification](https://agentstack.voostack.com/l/skill-redtropig-harness-anchor-init-verification) — Skill · Free · security-reviewed — `agentstack add skill-redtropig-harness-anchor-init-verification` Use at start of work, after env changes (deps/branch/OS), or when something stops working. Runs init.sh health check; treats failures as blocking. - [Feature State Keeper](https://agentstack.voostack.com/l/skill-redtropig-harness-anchor-feature-state-keeper) — Skill · Free · security-reviewed — `agentstack add skill-redtropig-harness-anchor-feature-state-keeper` Use when starting, advancing, finishing, or blocking a feature. Manages feature_list.json + progress.md + session-handoff.md. Default-FAIL enforced. - [Cpp Sanitizers](https://agentstack.voostack.com/l/skill-redtropig-harness-anchor-cpp-sanitizers) — Skill · Free · security-reviewed — `agentstack add skill-redtropig-harness-anchor-cpp-sanitizers` Use in C/C++ projects for crashes, hangs, UB, data races, memory errors. ASan/UBSan/TSan runtime checks. Build sanitizer config separately. - [Cpp Static Analysis](https://agentstack.voostack.com/l/skill-redtropig-harness-anchor-cpp-static-analysis) — Skill · Free · security-reviewed — `agentstack add skill-redtropig-harness-anchor-cpp-static-analysis` Use in C/C++ projects when reviewing changes or hunting bugs. Runs clang-tidy/cppcheck/IWYU. Needs compile_commands.json. Changed lines only. - [Self Correction Loop](https://agentstack.voostack.com/l/skill-redtropig-harness-anchor-self-correction-loop) — Skill · Free · security-reviewed — `agentstack add skill-redtropig-harness-anchor-self-correction-loop` Use when a hook/tool returns a warning, lint/type/build error, or test failure after your edit. Iterate evidence-first; stop when verification passes. --- Seller on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Install any with `agentstack add `.