phrazzld/harness
skills/harness/SKILL.md
Build and repair Spellbook primitives: skills, shared doctrine, provider roster, harness configs, gates, evals, bootstrap, and sync logic. Use for "improve the harness", "bootstrap is wrong", "AGENTS.md is stale", "skill health", "eval skill", "sync primitives", "roster defaults". Trigger: /harness, /skill, /primitive.
$ install --global
skillsauthnpx skillsauth add phrazzld/agent-skills harnessInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
Security Scan Results
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
3
Scanners Passed
9
Scanners in report
Clean
TrivyContainer and dependency vulnerability scanner
95%
Clean
SemgrepStatic code analysis for vulnerabilities
95%
Clean
mcp-scan (Snyk)Model Context Protocol security validation
95%
Skipped
Snyk (dep)Open source security scanning
50%
Skipped
Socket.devSupply chain security analysis
50%
Skipped
VirusTotalMulti-engine malware detection
50%
Skipped
CrowdStrikeAdvanced threat intelligence
50%
Skipped
OSV-ScannerOpen Source Vulnerability database check
50%
Skipped
OWASP Dep-Check
50%
Last scanned: May 28, 2026, 6:12 AM280.8s10 files scanned
SKILL.md
- name:
- harness
- description:
- |
- Build and repair Spellbook primitives:
- skills, shared doctrine, provider
- Trigger:
- /harness, /skill, /primitive.
- argument-hint:
- [create|eval|lint|convert|sync|engineer|audit|models] [target]
/harness
Mutate the harness. Keep it thin.
Route
| Need | Load |
|---|---|
| create skill/agent | references/mode-create.md |
| eval skill | references/mode-eval.md |
| lint skill | references/mode-lint.md |
| convert agent/skill | references/mode-convert.md |
| sync externals | references/mode-sync.md |
| engineer doctrine/gates/hooks | references/mode-engineer.md |
| audit catalog | references/mode-audit.md |
| open-model defaults | references/open-model-roster.md |
Contract
- Fix root cause in the highest-leverage layer: type/test/hook/gate/skill/ AGENTS, in that order.
- Prefer deletion. Harness prose is context tax.
- Cross-harness first: Claude, Codex, Pi. Filesystem +
SKILL.mdis primary. - Skills stay self-contained: scripts/references under the skill; state roots from invoking repo.
- Spellbook source skills live in
skills/; repo-local.agents/skills/and harness-specific skill bridge dirs are/seedoutput for consumer repos. - Generated/root
AGENTS.mdis a router, not a manual. Keep non-obvious facts only. - System bootstrap exposes the full first-party skill catalog; repo-local vendoring is exceptional and must earn its complexity.
- Provider CLIs are tools. Do not wrap them in semantic orchestration unless a shaped ticket explicitly asks.
Delegation Floor
If a provider roster is available (repo .spellbook/agents.yaml or system ~/.spellbook/agents.yaml), dispatch two or more providers for
substantive harness work and record receipts. Use lanes for doctrine critique,
runtime compatibility, gate design, and regression risk. Give each lane scoped
files and expected output; the lead owns final semantics, verification, and
receipt evidence. Direct work is for mechanical commands, emergency unblocks,
explicit user-forbidden delegation, or fewer than two available providers.
Do not treat a missing repo-local roster as a waiver. Run the resolver-backed
probe, which falls back to the system Spellbook roster:
python3 $SPELLBOOK_ROOT/scripts/probe-agent-roster.py.
Native in-thread subagents may supplement the investigation, but they do not
satisfy the roster floor. Count only configured provider ids in receipts and
final roster reports.
Quality Bar
SKILL.mdencodes judgment, not a procedure the model already knows.- Put long mode detail in
references/; keep the entry file short. - Ad-hoc roster lanes beat static project subagents unless tool permissions must be isolated.
- New mechanisms include a gate, eval, or smoke path.
- Every run ends clean: no untracked or modified files.
Gotchas
- Stale AGENTS prose is worse than missing prose.
- Duplicated repo-local skill copies are usually stale context unless a repo needs checked-in vendored harness state.
- Regexes over agent prose are usually the wrong boundary.
- If a rule matters, enforce it outside prose.
Related Skills
phrazzld/roster
tools
VerifiedTrustedCommunity
Enumerates the peer AI agent CLIs installed on this machine (codex, claude, pi, opencode, cursor-agent, grok, agy, hermes, thinktank) and how to invoke each headlessly. A capability map, not a quota: useful for fresh-context adversarial review on a different model family, second opinions, competing attempts, and wide benches. Use when: "ask codex", "ask another model", "second opinion", "cross-model review", "what AI tools do I have", "other agents", "different model family", "adversarial critique from another provider". Trigger: /roster.
13SKILL.mdUpdated Jun 11, 2026
phrazzld/sprites
development
VerifiedTrustedCommunity
Run lane cards on Fly Sprites: remote, isolated, scale-to-zero sandboxes for heavy or parallel agent work. Golden-checkpoint provisioning so lanes start on a ready sprite with zero setup tokens. Use when: "run this on a sprite", "remote lane", "offload to a sandbox", "dispatch to sprites", "bake a sprite", "sprite fleet", heavy/long-running/parallel sub-agent work that should not run on this machine. Trigger: /sprites, /sprite-lane.
13SKILL.mdUpdated Jun 10, 2026
phrazzld/dispatch
testing
VerifiedTrustedCommunity
Compose and launch roster-backed specialist lanes with prompt-native lane cards and receipts. Use when: "dispatch agents", "use subagents", "compose a team", "run provider lanes", "make lane cards". Trigger: /dispatch, /subagents, /lanes.
13SKILL.mdUpdated Jun 9, 2026
phrazzld/orient
tools
VerifiedTrustedCommunity
Fast session-start repository orientation from live local evidence. Use when: "orient yourself", "start of session", "new session", "where are we", "catch me up before acting", "what should I do next", after compaction, after switching worktrees, or before choosing a Harness Kit workflow. Trigger: /orient, /ground, /session-start.
13SKILL.mdUpdated Jun 7, 2026