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/bjorn-ingmanson/thefroject-plugins/intelligencegit clone --depth 1 https://github.com/bjorn-ingmanson/thefroject-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 | $0.00000 | $0.00457 |
| Opus 5 | $0.00000 | $0.00229 |
| Sonnet 5 | $0.00000 | $0.00091 |
| Haiku 4.5 | $0.00000 | $0.00046 |
Grade A, and why
intelligence 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 — 39 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/intelligence — GTM Learnings Log
Capture and retrieve GTM intelligence so wins, losses, and objections become reusable knowledge instead of tribal memory.
Modes
/intelligence add [what you learned]— log a new insight/intelligence find [topic]— search existing entries/intelligence review— summarize what has been captured in the last 30 days
When you add
Walk the user through a short capture:
- Source — campaign, call, experiment, feedback, manual hunch.
- Insight — one-sentence takeaway. Concrete, not vague. "Subject lines with the prospect's city outperform generic geo references by ~20% in enterprise" beats "personalization works."
- Segment — ICP, role, industry, deal stage. Which slice this applies to.
- Confidence —
hypothesis(one data point),validated(repeatable in one channel),proven(holds across channels or over time). - Evidence — link or note for where the insight came from.
Append to context/intelligence.md under the right section (Wins / Losses / Objections / Messaging / Channels). Create the file with these sections if it does not exist. One bullet per learning, tagged with segment and confidence.
When you find
Search context/intelligence.md and related outputs/ files for matching entries. Return:
- Top 3 most relevant entries with their confidence level.
- Any conflicting entries (one says X works, another says it does not) flagged for review.
- A suggested next action ("you have a validated learning here — apply it to [current work]").
When you review
Summarize additions from the last 30 days: what was learned, which segments were covered, which are underrepresented. Flag stale hypotheses (older than 60 days, never validated) for retirement.
Usage: /intelligence [add|find|review] [optional text]
Examples:
/intelligence add short subject lines beat long ones in cold outreach to ops leaders/intelligence find pricing objections for mid-market/intelligence review
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 · 39 lines · 0 tokens per session scan A 263731b74150
intelligence is a command published in the GitHub repository bjorn-ingmanson/thefroject-plugins (1 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 457 tokens. 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.