Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add L3DigitalNet/Claude-Code-Plugins/plugin install spec-pipelineWrote 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/l3digitalnet/claude-code-plugins/execute-phase)<a href="https://agentmods.dev/skills/l3digitalnet/claude-code-plugins/execute-phase"><img src="https://agentmods.dev/badge/skills/l3digitalnet/claude-code-plugins/execute-phase/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/l3digitalnet/claude-code-plugins/execute-phase"><img src="https://agentmods.dev/badge/skills/l3digitalnet/claude-code-plugins/execute-phase.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 | $0.00051 | $0.03344 |
| Opus 5.5 | $0.00020 | $0.01338 |
| Sonnet 5.5 | $0.00010 | $0.00669 |
| Haiku 4.5 | $0.00005 | $0.00334 |
Grade A, and why
execute-phase 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 1mo 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 — 151 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Autonomous Phase Execution
Execute the next phase of the project named in $ARGUMENTS end-to-end, autonomously, in this session. Do not stop for input unless genuinely blocked (see HALT CONDITIONS). Stop when the phase is complete. Do not continue to the next phase; that is a separate session.
Preconditions (verify before starting)
- Session permission mode permits unattended workflow runs. If a review workflow's first run prompts for approval, approve with "don't ask again for this path" so later phases run silently.
- The
/codex-reviewskill (Codex CLI) and ultracode workflow support are available — the review gates hard-require both. If either is missing, HALT; do not substitute an ad-hoc review and mark the gate passed. - Working tree is clean or its state is understood. Note current branch.
Orchestration model
- Main session model: Opus (orchestrator + synthesis + convergence judgment).
- Review allocation:
- Spec and plan gates: exactly ONE
ultracodeworkflow pass (panel review of the raw artifact), then/codex-reviewto convergence. The single workflow pass catches structural problems; Codex handles the iterative tail on idle credits. - Final review (post-implementation):
/codex-reviewonly. Noultracodeworkflow at this gate.
- Spec and plan gates: exactly ONE
- Workflow subagent routing: every
ultracodeworkflow MUST use Sonnet worker subagents; reserve Opus subagents only for genuinely complex sub-tasks (e.g. cross-document adversarial comparison). State this constraint explicitly in each workflow trigger so it is encoded into the generated script.
References
Shared standards live in ${CLAUDE_PLUGIN_ROOT}/references/. They are the rubric for both authoring and the review gates.
- Spec construction — core:
${CLAUDE_PLUGIN_ROOT}/references/spec-construction.md - Spec construction — phase delta:
${CLAUDE_PLUGIN_ROOT}/references/spec-construction-phase.md - Plan construction standard:
${CLAUDE_PLUGIN_ROOT}/references/plan-construction.md
When this skill writes or reviews a phase spec, the standard is the core PLUS the phase delta (read both). The phase delta governs inheritance: cite the master design and predecessor-phase contracts; restate only load-bearing inherited invariants; do not re-derive system architecture.
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.
- 1mo ago First seen · 151 lines · 51 tokens per session scan A e57e53b9804a
execute-phase is a skill published in the GitHub repository L3DigitalNet/Claude-Code-Plugins (8 stars, last pushed 1mo ago), licensed MIT. It adds 51 tokens to every session and 3,344 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-09-04.
Other skills, from other repositories
engram-testing-coverage
TDD and coverage standards for Engram. Trigger: When implementing behavior changes in any package.
conductor-implement
Execute tasks from a track's implementation plan following TDD workflow.
principle-test-behavior-not-implementation
Apply when you write, change, or keep a test. Assert what the code's users can observe, so that the test fails when that behavior breaks and keeps passing when only the internals change.
iterative-development
TDD iteration loops using Claude Code Stop hooks - runs tests after each response, feeds failures back automatically.
python
Python development with ruff, mypy, pytest - TDD and type safety.
tdd
This skill should be used when the user wants to implement features or fix bugs using test-driven development. Enforces the RED-GREEN-REFACTOR cycle with vertical slicing, context isolation between test writing and implementation, human checkpoints, and auto-test feedback loops. Uses multi-agent orchestration with the…