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 agentmods add skills/closedloop-ai/claude-plugins/present-localnpx skills add closedloop-ai/claude-plugins --skill present-localgit clone --depth 1 https://github.com/closedloop-ai/claude-pluginsWhat 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 | $0.00136 | $0.03650 |
| Opus 5 | $0.00068 | $0.01825 |
| Sonnet 5 | $0.00027 | $0.00730 |
| Haiku 4.5 | $0.00014 | $0.00365 |
Grade A, and why
present-local 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 2d 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 — 304 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Local-Mode Code Review Presenter
This skill is the canonical presenter for /code-review local mode at stage_29_present. It is split out of commands/start.md so the orchestration spine stays lean; the orchestrator invokes it when MODE=local and stage_29_present is reached.
Gate A hygiene-only early-exit is not in this skill. That path is mode-agnostic (fires for both MODE=local and MODE=github) and the hygiene presentation lives in start.md adjacent to the Gate A definition — the orchestrator handles it inline, not via this skill.
Local Mode: Present Results (stage_29_present, MODE=local)
Mark "Present findings by severity" in_progress.
Render the report below. Three text conventions run through this template, so it stays clear which lines you emit verbatim and which are directions to you:
##section headers (Repo Hygiene, BLOCKING, …) are the report's own structure — emit them as written, with the live[count]substituted.- Fenced code blocks are card/footer templates — instantiate one per finding (or per stat block), substituting the
{PLACEHOLDER}and[bracketed]fields. [bracketed]and{BRACED}tokens are instructions or substitution points, never literal output.
Output in this format:
# Code Review Results
**Scope:** [staged/branch/files]
**Files Reviewed:** [count]
Reviewer Fleet block (PLN-725 Phase 9 / v2.23.0). Do NOT write the Reviewers / Model Routing / Fleet lines from scratch. Run the canonical renderer and embed its output verbatim:
python "${CLAUDE_PLUGIN_ROOT}/tools/python/code_review_helpers.py" render-fleet-summary --cr-dir <CR_DIR>
The renderer consumes <CR_DIR>/spawn.json (sections: spec — intended fleet from stage_19b; verification — runtime tally from stage_20b; route — model assignments from Gate B). The output is a deterministic markdown block of 2–9 lines — 2–4 for the core Reviewers / Model Routing / Fleet section, plus up to 5 conditional note bullets — covering:
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.
- 2d ago First seen · 304 lines · 136 tokens per session scan A d60942b3692f
present-local is a skill published in the GitHub repository closedloop-ai/claude-plugins (103 stars, last pushed 4d ago), licensed Apache-2.0. It adds 136 tokens to every session and 3,650 once invoked, about $0.0007 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 2026-08-30.
Other skills, from other repositories
agent-code-analyzer
Agent skill for code-analyzer - invoke with $agent-code-analyzer.
foundry-config-setup
Resolve missing setup caused by a hardcoded Foundry project endpoint or model in a sample. Use when a sample fails because it uses a placeholder/hardcoded projectendpoint (for example "https://your-project.services.ai.azure.com") or a hardcoded model instead of reading them from the environment.
evolve
Start or monitor an evolutionary development loop.
agent-memory
../../../engineering/agent-memory/skills/agent-memory/SKILL.md.
agile-product-owner
../../../product-team/agile-product-owner/skills/agile-product-owner/SKILL.md.
dogfood
Systematically explore and test a mobile app on iOS/Android with agent-device to find bugs, UX issues, and other problems. Use when asked to dogfood, QA, exploratory test, find issues, bug hunt, or test this app on mobile.