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/discovergit 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 | $0.00015 | $0.00998 |
| Opus 5 | $0.00008 | $0.00499 |
| Sonnet 5 | $0.00003 | $0.00200 |
| Haiku 4.5 | $0.00002 | $0.00100 |
Grade A, and why
discover 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 — 48 lines — stays where its author put it; the contents beside it link to each section on GitHub.
When the user invokes /discover, follow this process:
1. Resolve names to real handles
Call lookup_brands({ query }). It searches Adology's central brand directory and returns, for each match, the category, website, domain, and whatever handles the directory holds — Instagram, TikTok, YouTube, X, LinkedIn, and the Ad Library page id — already normalized to the shape author_portfolio_context accepts. It is free, reads only, and adds nothing.
A directory entry may carry only one or two channels. That is the real state of the entry, not an error; report which channels exist rather than inventing the missing ones. If hasMore comes back true, the directory holds more matches than the page you asked for.
2. Find who is already doing the thing
When the ask is about content rather than company names — "who is running founder-led video", "which competitors talk about refill packs" — search the data instead of the directory. In a project that already has scope, search_all({ projectId, query }) runs a keyword search over item analysis text and returns the matching posts ranked by engagement, each with its brand and URL. For a meaning-based recall rather than keyword matching, use analyze({ projectId, query, mode: "semantic" }).
The brand names on those results are discovery leads in their own right: someone whose content keeps surfacing is a candidate to track. Feed the promising names back through lookup_brands to get their handles.
Creators work the same way. If a creator is not in the directory, ask the user for the handle and platform — that is enough to track them.
3. Present the candidates
Number the list so the user can answer with numbers. For each candidate give the name, the category, the channels that actually exist for it, and one line on why it matches the ask. Keep content examples in a separate short list, with the brand behind each one named.
4. Add what the user picks
Tracking happens on the portfolio, not on a project. Read the current state first with read_portfolio_context({ portfolioId }), then merge the new entries with author_portfolio_context({ portfolioId, upsertItems }). Each item needs an id, a kind (brand, influencer, search, discussion, trend-term, niche, seo), and its identifiers. A brand also needs a role — own for the user's own brand, competitor, adjacent, or inspiration for the rest — and a handles object keyed by platform (instagram, tiktok, facebook, youtube, adLibrary), or {} when the directory had none. kind is one bare token; role and every other attribute is its own field.
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 · 48 lines · 15 tokens per session scan A 9e6095ceda0f
discover is a command published in the GitHub repository adologyai/content-intelligence-plugin (2 stars, last pushed 27d ago), licensed Apache-2.0. It adds 15 tokens to every session and 998 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.
constitution
Create or update the project constitution from interactive or provided principle inputs.