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 commands/adologyai/content-intelligence-plugin/analyzegit clone --depth 1 https://github.com/adologyai/content-intelligence-pluginWhat 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 | $0.00013 | $0.01292 |
| Opus 5 | $0.00006 | $0.00646 |
| Sonnet 5 | $0.00003 | $0.00258 |
| Haiku 4.5 | $0.00001 | $0.00129 |
Grade A, and why
analyze 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 — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.
When the user invokes /analyze, follow this process:
1. Land in a scope
A read is only as good as what it is about. Orient with whoami, then list_portfolios, then list_projects({ portfolioId }). Reuse a project that already covers the subject, or create_project for a fresh one — there is no special home project.
Call get_project before analyzing. It returns the project's dataScope (the tracked set of sources it reads) plus per-source access: expiredSources have data only through a date, ungrantedSources are tracked but not yet acquired. That list is the denominator behind every number you are about to report. A project with an empty scope reads the portfolio's whole tracked universe until it is narrowed.
To point the project at exactly the sources this question is about, use update_project_scope: add extends, remove trims, replace pins the scope to exactly the sources you name. Adding sources the pool already covers is free and instant.
2. See which dimensions exist
Call list_labels({ projectId }) for the label dimensions and top values actually present in this scope. Use those exact names in labelFilter and get_table_data rows — a dimension the scope does not carry matches nothing, so an invented name turns the whole read into an empty result. If list_labels reports nothing, the scope holds no labeled items yet: analyze on engagement and content instead, and say that labels are unavailable.
3. Read what is already there
analyze({ projectId, query }) is the workhorse. It returns posts with their creative analysis — hookMechanism, creativeConcept, adDescription, transcript, oneLineInsight — from the resolved scope. Choose the retrieval that matches the question:
distribution: "balanced"(default) for a representative read across sources.distribution: "top"(withsortMetric) for the highest-engagement content per source.distribution: "exhaustive"withsortBy: "likesMultiple"(or another*Multiple) for a real ranked leaderboard over the full filtered set, withtotalEstimatedandnextOffsetfor paging.mode: "semantic"when the ask is a meaning ("posts that make sustainability feel effortless") rather than a filter.
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 · 63 lines · 13 tokens per session scan A a7670ccecbc5
analyze is a command published in the GitHub repository adologyai/content-intelligence-plugin (2 stars, last pushed 27d ago), licensed Apache-2.0. It adds 13 tokens to every session and 1,292 once invoked, about $0.0001 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 2026-08-31.
Other commands, from other repositories
git
Git operations with intelligent commit messages and workflow optimization.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.