Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/xberg-io/crawlbergnpx agentmods add skills/xberg-io/crawlberg/dev-cycleWrote 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/skills/xberg-io/crawlberg/dev-cycle)<a href="https://agentmods.dev/skills/xberg-io/crawlberg/dev-cycle"><img src="https://agentmods.dev/badge/skills/xberg-io/crawlberg/dev-cycle/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/skills/xberg-io/crawlberg/dev-cycle"><img src="https://agentmods.dev/badge/skills/xberg-io/crawlberg/dev-cycle.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00086 | $0.00677 |
| Opus 5.5 | $0.00034 | $0.00271 |
| Sonnet 5.5 | $0.00017 | $0.00135 |
| Haiku 4.5 | $0.00009 | $0.00068 |
Grade A, and why
dev-cycle 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 4d 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 — 55 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Iteration loops are codified as Taskfile tasks. Prefer them over ad-hoc commands.
After alef changes
task alef:install # cargo install --path ../alef/crates/alef-cli
task alef:generate # alef all --clean --format=false
task alef:format # explicit Alef formatting; task format excludes this
VERSION=0.15.30 task alef:bump # bump pin in alef.toml + reinstall + regen
After crawlberg-core changes
task build # core-only
task build:bindings # all bindings
task build:all # core + all bindings
E2E cycles
task e2e:generate # regenerate all language test suites from fixtures
task e2e:build # build bindings and the generated mock-server for e2e
task e2e:test # run generated e2e suites
task e2e:all # generate + build + run generated e2e suites
Cleanup
task clean # per-language artifacts
task clean:workspace # cargo target + alef IR cache + legacy mock-server bins
task clean:e2e # venvs, node_modules, _build, lockfiles, vendor/
task clean:full # all of the above
Gotchas (codified, but worth knowing)
- One mock-server binary.
e2e/rust/src/main.rsis alef-generated and is the binary all language conftests spawn. (An oldertools/mock-serverwas removed; only thetask cleandescription still mentions it.)task e2e:buildbuilds the right one ate2e/rust/target/release/mock-server. - Python venv stale
.so. Aftertask python:build:dev, the e2e venv ate2e/python/.venvkeeps a stale extension.task python:cyclerunsuv sync --reinstallto refresh. - Elixir precompiled NIF. Rustler's precompiled binary is tagged at the package's release version and lags local source.
CRAWLBERG_BUILD=1is set in.task/languages/elixir.yml::e2e:testso the e2e suite always builds the NIF from local source. - Generated e2e files.
e2e/<lang>/is alef-generated — never hand-edit. Modify fixtures or alef codegen, thentask alef:generate.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 4d ago Changed · +6 lines · -3 tokens per session 2ef23810fed9
- 1mo ago Changed 26b09cf7014f
- 1mo ago First seen · 49 lines · 89 tokens per session scan A 27de14aee517
dev-cycle is a skill published in the GitHub repository xberg-io/crawlberg (186 stars, last pushed 2d ago), licensed MIT. It adds 86 tokens to every session and 677 once invoked, about $0.0003 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 2026-08-30.
Other skills, from other repositories
tree-sitter-language-pack-extracting-code-structure
Use when the user wants structured code metadata from a source file — functions, classes, imports, exports, symbols, docstrings, comments, or syntax diagnostics. Covers ts-pack process feature flags, the JSON result shape, and the default feature set.
tree-sitter-language-pack-parsing-source
Use when the user wants a tree-sitter syntax tree for a source file — an s-expression dump or JSON tree. Covers ts-pack parse, language auto-detection vs --language, stdin input, and reading haserrors.
pinchtab-dev
Develop and contribute to the PinchTab project. Use when working on PinchTab source code, adding features, fixing bugs, running tests, or preparing PRs. Triggers on "work on pinchtab", "pinchtab development", "contribute to pinchtab", "fix pinchtab bug", "add pinchtab feature".
debugging-failures
Diagnose a failing Ginkgo suite as an agent — always run with --json-report into a predictable temp/gitignored location, read the terminal verdict line, then use jq to extract structured failure details (name, message, file:line, panic value, captured logs). Covers the panicked-vs-failed trap, panic locations pointing…
tree-sitter-language-pack
Parse and extract code intelligence from 372 programming languages using tree-sitter grammars. Use when writing code that parses source, extracts structure/imports/exports/symbols/docstrings/comments, detects a language, runs syntax diagnostics, or produces syntax-aware chunks for LLMs — in Rust, Python…
tree-sitter-language-pack-detecting-languages
Use when the user wants to know which programming language a file or snippet is. Covers implicit detection in ts-pack parse/process, confirming support with ts-pack list/info, and the SDK detection functions for path, extension, and raw content.