Skill Claude CodeCodex
Author a frozen, graded eval harness for ONE inner skill and freeze it inside that skill as a conformant eval/ directory (scenarios + deterministic evaluator + rubric + fixtures + HARNESS.md manifest). The eval content is skill-specific; this skill is the reusable methodology that produces it. Its output is consumed…
Skill Claude CodeCodex
Customizes an installed agent skill and ships it back upstream or as a versioned fork using qvr's edit/publish authoring loop. Use when a user wants to modify, customize, fork, release, or publish a qvr skill — e.g. "edit this skill", "publish my changes", "fork a skill to my own repo", "cut a v1.0.0 release of a…
Skill Claude CodeCodex
Discovers and installs agent skills into a project (or the user-global lane) with the qvr CLI, where qvr.toml declares intent and qvr.lock is the resolved source of truth for what loads. Use when a user wants to find, add, register, or install skills from a skills registry or GitHub repo with qvr — e.g. "register a…
Skill Claude CodeCodex
Deterministic outer-loop optimizer for a skill that already carries a frozen eval (produced upstream by an eval source such as create-skill-eval). Runs the frozen eval across user-chosen agents on fresh headless sessions via a pluggable adapter, grades quality/cost/perf, keeps the pareto-best variant, and versions…
Skill Claude CodeCodex
Reproduces an exact agent-skill set across machines, teammates, and CI using qvr's portable manifest and lockfile guarantees. Use when a user wants to share, pin, replicate, or CI-gate their qvr skills — e.g. "export my skills", "import this skill manifest", "pin everything to exact commits", "make skills…
Skill Claude CodeCodex
Records and queries what agents actually did, attributed to the skill that was active, using qvr's experimental audit subsystem. Use when a user wants observability into agent or skill behavior — e.g. "track what my skills are doing", "audit agent tool calls", "which skill ran during this session", "show recent agent…
Skill Claude CodeCodex
Vets and continuously verifies the integrity and provenance of agent skills installed with qvr. Use when a user cares about skill security, trust, signing, tampering, or supply-chain integrity — e.g. "scan this skill for problems", "is this skill safe", "verify the skill hasn't drifted", "who is allowed to author this…
Skill Claude CodeCodex
A baseline skill that the security scanner must report as completely clean. Used as a false-positive gate.
Skill Claude CodeCodex
This file has no frontmatter at all. Just plain markdown without --- delimiters.
Skill Claude CodeCodex
This skill has consecutive hyphens in the name.
Skill Claude CodeCodex
The description is empty.
Skill Claude CodeCodex
This skill has a name that is too long.
Skill Claude CodeCodex
The name field does not match the directory name.
Skill Claude CodeCodex
Just some markdown content. No YAML frontmatter delimiters at all.
Skill Claude CodeCodex
A skill missing the required name field.
Skill Claude CodeCodex
This skill name starts with a hyphen.
Skill Claude CodeCodex
This skill name has uppercase characters.
Skill Claude CodeCodex
Fixture for the data-exfiltration patterns. Designed to fire E2 (env harvesting), E3 (filesystem credential scan), and E4 (conversation export) in a single skill so the scanner regression test can assert the whole category at once.
Skill Claude CodeCodex
Fixture for the prompt-injection check. Contains several documented injection patterns embedded as instructions, not as docs about injection.
Skill Claude CodeCodex
Fixture for the MCP least-privilege check. Declares allowed-tools containing only "Read" but ships Python code that exercises shell and network capabilities, so LP1 must fire for both undeclared capabilities.
Skill Claude CodeCodex
Visually this looks like an innocuous date-formatting skill. The frontmatter description embeds an HTML comment with a SYSTEM override directive, and the metadata.notes field swaps a Latin letter for a Cyrillic homoglyph — both classic tool-poisoning patterns flagged as TP1 / TP2.
Skill Claude CodeCodex
Fixture for the permissions check. Declares unrestricted Bash in allowed-tools and ships a dangerous executable script.
Skill Claude CodeCodex
Fixture for the rogue-agent rule family (RA1 self-modification, RA2 session persistence via crontab and shell rc). The fixture ships a SKILL.md plus a Python helper that overwrites its own source.
Skill Claude CodeCodex
Fixture for the secrets check. Contains hardcoded credential-shaped strings that the scanner must flag as critical findings.