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.
git clone --depth 1 https://github.com/Birfy/agentdescentWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/commands/birfy/agentdescent/algorithms)<a href="https://agentmods.dev/commands/birfy/agentdescent/algorithms"><img src="https://agentmods.dev/badge/commands/birfy/agentdescent/algorithms/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/birfy/agentdescent/algorithms"><img src="https://agentmods.dev/badge/commands/birfy/agentdescent/algorithms.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What 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 5.1 | $0.00020 | $0.00378 |
| Opus 5.5 | $0.00008 | $0.00151 |
| Sonnet 5.5 | $0.00004 | $0.00076 |
| Haiku 4.5 | $0.00002 | $0.00038 |
Grade A, and why
algorithms 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.
What it actually says
Use the agentdescent skill / MCP tools. $ARGUMENTS chooses the verb; the data
is the same as agentdescent algorithms list / show and the MCP tools
list_algorithms / describe_algorithm. Never invent a name.
Parse $ARGUMENTS (trim; empty means list):
list[optional--kind K]: calllist_algorithms(oragentdescent algorithms list [--kind K] [--json]). Show each name, one-line summary, kinds, and fidelity. If the user named a kind, filter to it.show <name>: calldescribe_algorithm(oragentdescent algorithms show <name>). Show the full card (params, defaults, extra cost, what it changes). Stop here unless they ask to run it.run <name> <path>[optionalcases.jsonl] [optional--param k=v]: build a spec for the path withalgorithmset to that name (and only the params they gave — validate withdescribe_algorithm/showfirst). Rundoctor,plan, show the resolved algorithm card and estimate, and wait for my yes beforestart. Same apply/cancel/resume rules as/evolve.
If they only named a method with no path, show it and ask whether to run.
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 · 25 lines · 20 tokens per session scan A 41b6075c7f40
algorithms is a command published in the GitHub repository Birfy/agentdescent (201 stars, last pushed today), licensed MIT. It adds 20 tokens to every session and 378 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-10-28.
Other commands, from other repositories
test-feature
Test a React Native feature on the running simulator/emulator. Verifies UI, user flows, and internal state. Generates a persistent Maestro test file.
nav-graph
Extract, inspect, and query the app navigation graph — a complete map of all screens and navigators.
check-env
Check that the fenced React Native session, Metro, app target, and device inventory are ready for testing.
run-workflow
Validate and establish the proven rn-dev-agent operating sequence before a real React Native journey — declared package manager and dependencies, read-only inventory, typed session recovery, one exclusive device, managed integration and Metro, only the requested proof, reverse-order cleanup.
observe
Show the observability web UI URL (it autostarts with the session); stop or restart it.
rn-feature-dev
Guided feature development for React Native — explore codebase, design architecture, implement, verify live on device, and review quality.