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/intellegix/intellegix-code-agent-toolkit/raken-apigit clone --depth 1 https://github.com/intellegix/intellegix-code-agent-toolkitWhat 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 | $0.01210 |
| Opus 5 | $0.00000 | $0.00605 |
| Sonnet 5 | $0.00000 | $0.00242 |
| Haiku 4.5 | $0.00000 | $0.00121 |
Grade A, and why
raken-api 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 — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/raken-api -- Raken API Context Loader
Load Raken Public API 3.0 documentation into active context. Run this at the start of any Raken API work session to ground all decisions in the actual documentation.
This is a local context loader -- no Perplexity, no external queries. For external research, use /raken-perplexity after loading context with this command.
Usage
- /raken-api -- Load full API context (all endpoints, auth, patterns)
- /raken-api ARGUMENTS -- Load filtered context focused on specific resource
Examples: /raken-api timeCards, /raken-api members, /raken-api dailyReports oauth
Documentation Directory
C:/Users/AustinKidwell/ASR Dropbox/Austin Kidwell/08_Financial_PayrollOperations/Certified Payroll/Raken API
Execution
Step 1: Locate and Validate Cache
Check for the compiled reference cache:
{docs_dir}/raken-api-reference.md
If the file exists: Check its modification date. If modified within the last 7 days, proceed to Step 3. If older than 7 days, proceed to Step 2.
If the file does NOT exist: Proceed to Step 2.
If ARGUMENTS contains "rebuild": Always proceed to Step 2 regardless of cache age.
Step 2: Rebuild Cache (only when needed)
Read the following source files from the documentation directory and compile them into raken-api-reference.md. This step runs rarely -- only on first invocation or when cache is stale.
- Read README_API_TESTING.md -- extract OAuth credentials, endpoint categories, test workflow
- Read Raken+Public+API+3.csv (all 1807 lines) -- extract and group by resource type: endpoint paths, HTTP methods, query parameters (name, description, optional/required, constraints), response fields (path, type, description)
- Read Raken_API_SOP.html -- extract OAuth flow steps, token management, troubleshooting, security practices
- Read raken_make_calls.py -- extract request patterns, base URL, headers, pagination, error handling
- Read raken_get_token.py and raken_auth_url.py -- extract full OAuth flow code patterns
- Read Raken Public API 3.0 Developer Guide.pdf (pages 1-20) -- extract any endpoints, data models, or patterns not already captured from the CSV
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 · 93 lines · 0 tokens per session scan A 04013a904191
raken-api is a command published in the GitHub repository intellegix/intellegix-code-agent-toolkit (57 stars, last pushed 8d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,210 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 2026-08-30.
Other commands, from other repositories
README
Git workflow and quality assurance commands for the claude-skills repository.
agentlas-cloud
Staff a task only from the signed-in owner's Agent Cloud agents.
dispatcher
Pick the next-best repo to work on across the portfolio — rank free repos, recommend one, claim its lease atomically, and route to the entry command.
tldr
Re-apply TLDR rules for this turn (verdict first, no filler).
execute
Interactive workflow for workspace isolation, pane-delegated implementation, testing, review, and cleanup.
me-figure-discussion
Write or review thermal-fluid figure discussion with observation, physical mechanism, comparison, uncertainty, and claim limits.