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/comparegit 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 | $0.00011 | $0.01249 |
| Opus 5 | $0.00005 | $0.00624 |
| Sonnet 5 | $0.00002 | $0.00250 |
| Haiku 4.5 | $0.00001 | $0.00125 |
Grade A, and why
compare 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 yesterday.
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 — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.
When the user invokes /compare, follow this process:
1. Resolve both sides to tracked entities
Split the input on "vs", "versus", "compared to", "and", or "against". If you cannot identify exactly two subjects, ask which two.
Both sides have to be tracked before they can be compared. Orient with list_portfolios → list_projects({ portfolioId }), then call get_project and read its dataScope: the entity names it tracks are the names the read tools will match. aggregate({ groupBy: ["brand"] }) is the fastest way to see which names actually carry items.
If one side is not tracked anywhere in the project, say so before analyzing. Resolve its real handles with lookup_brands, add it to the portfolio's tracked universe with author_portfolio_context, then pull_data → show the quote → confirm_pull once the user approves the credits. A comparison against a brand with no data is not a comparison.
If the two brands live in different projects, run the same reads once per project and compare the results — say plainly that the two sides were read from different scopes and note any difference in coverage window.
2. Bind each read to one entity
Each tool names the entity filter differently, and using the wrong one silently compares the whole scope against itself:
query_items({ brand: ["Sephora"] })— the surest binding. It resolves the name against the project's tracked roster case-insensitively, and a name the project does not track comes back as anentityScopegap listing what is tracked, rather than as a scope-wide ranking dressed up as that brand's.analyze({ feedNames: ["Sephora"] })— applies in the sampled and exhaustive reads. Semantic mode retrieves by meaning across the scope and does not narrow onfeedNames, so bind the entity a different way when you use it.aggregate({ filters: { brand: [...] } })— a case-insensitive name filter, or group bybrandto get both sides in one call. A misspelled or untracked name yields empty groups rather than a gap notice, so confirm the spelling against agroupBy: ["brand"]pass first.get_table_data({ brands: [...] }), or better,columns: "focalVsRest"withfocalBrandset.get_creative_dna({ feedNames: [...] })orentities: [{ type, name }].
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.
- yesterday First seen · 68 lines · 11 tokens per session scan A f095372c3084
compare is a command published in the GitHub repository adologyai/content-intelligence-plugin (2 stars, last pushed 27d ago), licensed Apache-2.0. It adds 11 tokens to every session and 1,249 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
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.
constitution
Create or update the project constitution from interactive or provided principle inputs.
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.