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/evolve)<a href="https://agentmods.dev/commands/birfy/agentdescent/evolve"><img src="https://agentmods.dev/badge/commands/birfy/agentdescent/evolve/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/evolve"><img src="https://agentmods.dev/badge/commands/birfy/agentdescent/evolve.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 | $0.00019 | $0.00167 |
| Opus 5.5 | $0.00008 | $0.00067 |
| Sonnet 5.5 | $0.00004 | $0.00033 |
| Haiku 4.5 | $0.00002 | $0.00017 |
Grade A, and why
evolve 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 6d 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.
What it actually says
Use the agentdescent skill. The target is $ARGUMENTS (a path, optionally
followed by a cases file). Run doctor, build the spec, plan it, show me the
spec and the estimate, and wait for my yes before start.
If I named a method that is in agentdescent algorithms list (for example RRSI
or archive_selection), set algorithm in the spec (or pass --algorithm to
init) with its parameters and show me the resolved card and cost in the plan;
if I did not, use the kind's default recipe.
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.
- 6d ago Changed · +5 lines 90c263e64661
- 1mo ago First seen · 9 lines · 19 tokens per session scan A 9c070b24cea5
evolve is a command published in the GitHub repository Birfy/agentdescent (201 stars, last pushed today), licensed MIT. It adds 19 tokens to every session and 167 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 2026-09-08.
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.
qa-pr
Device-test a GitHub pull request on iOS simulator, Android emulator, and/or physical device. Installs the PR head via rn-dev-agent and reports pass/fail with repro steps and screenshots.
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.
lock-e2e
Promote a verified action into a frozen, locked e2e regression test. Runs the action once strict (no repair) via cdplocke2etest and freezes it to .rn-agent/e2e/ .yaml only if it passes. v1 supports param-free actions only.
octo-deliver
"Delivery phase - Review, validate, and test with multi-AI quality assurance".
octo-tdd
Test-driven development with red-green-refactor discipline.