Borrowing it
Nothing to install: this file belongs to IvanWng97/pixtuoid. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/IvanWng97/pixtuoid/main/.github/prompts/add-source.prompt.mdgit clone --depth 1 https://github.com/IvanWng97/pixtuoidWrote 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/ivanwng97/pixtuoid/add-source)<a href="https://agentmods.dev/commands/ivanwng97/pixtuoid/add-source"><img src="https://agentmods.dev/badge/commands/ivanwng97/pixtuoid/add-source.svg" alt="Measured on agentmods" 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 | $0.00013 | $0.01015 |
| Opus 5 | $0.00006 | $0.00508 |
| Sonnet 5 | $0.00003 | $0.00203 |
| Haiku 4.5 | $0.00001 | $0.00102 |
Grade A, and why
add-source scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured today.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Add a new agent-CLI Source
Wire up a new agent CLI (${input:name}) as a pixtuoid Source. This is not
a single-file change — read crates/pixtuoid-core/CLAUDE.md ("multi-source
decoding" / "Adding a new agent CLI") first, then:
- Implement the
Sourcetrait (hook-only CLI? skip it + the runtime wiring — settranscript: Noneand ship ahook.customdecoder + install target instead). Per-source JSONL format knowledge lives in the source's own decoder fn (injected intoJsonlWatchervia fn pointers), not a shared decoder. - Add ONE
SourceDescriptorrow insource/registry.rs(label prefix, decoders, hook keying, reducer caps) — itsnamefield IS the roster (registered_source_names()projectsREGISTRY; uniqueness pinned byregistered_source_names_are_unique), and the conformance test forces a coalescing fixture. - Wire it into
runtime/driver.rs::build_source_set(the one construction site, called byrun_async) — the registry gates conformance tests, not spawning, but a bridge test (build_source_set_wires_every_transcript_bearing_source_plus_the_hook_router) pins that set to the registry's transcript-bearing rows, so a registered-but-unwired source failsjust test. - If you add an
AgentEventvariant, add a matching arm toAgentEvent::agent_id()insource/mod.rs. - Update the four test areas that exercise the channel /
Source/ reducer together:tests/reducer/,tests/e2e.rs,tests/transport/socket.rs,tests/watcher/, plusruntime/driver.rson the binary side. - Add a captured fixture under
tests/sources/fixtures/<name>/<scenario>/(a unique lifecycle also gets atests/sources/<cli>.rsmodule). The test layout + add-a-CLI steps are incrates/pixtuoid-core/tests/CLAUDE.md. - Add a row to
site/src/sources.json(the tool × OS matrix + README glimpse);tests/supported_sources_manifest.rspins itssupportedset toregistered_source_names(), so a new source fails that test until the row exists. Thenjust gen-readmeto sync the README's Supported Tools section. - Add the per-source badge hue: a
Theme::source(SourceColors) field in EVERY theme file + amatcharm intui/widgets/dashboard.rs::dashboard_line(every_registry_source_has_a_non_fallback_badge_color+source_colors_cover_every_registered_sourcefail otherwise). - If the CLI has a custom config/home root, add a
pub fn <cli>_home()honoring its*_HOMEenv precedence, called from BOTH the watcher'sdefault_paths()AND the installer'sdefault_config_path()(one function, two consumers). - Cover the source in the binary's TWO per-source INTEGRATION goldens (own test
binaries, NOT built by
-p pixtuoid --lib): regenerate thesources --jsongoldencrates/pixtuoid/tests/snapshots/cli/sources.json(SNAPSHOTS=overwrite cargo test -p pixtuoid --test cli_json), and add aWireCase+ per-source render test incrates/pixtuoid/tests/wire_to_pixels.rs(hook-only →DecodeKind::Hook+Transport::Hook), elsesources_json_lists_every_source_in_an_isolated_home/wire_matrix_covers_every_registered_sourcered.
These cross-crate deps are caught only by just preflight's FULL run, not the
targeted source/install suites — and a -p <crate> --lib run builds NEITHER
integration binary in step 10 (kimi #692 shipped both red past a green --lib
run and a multi-lens review). Respect the architecture invariants (no terminal
deps in pixtuoid-core/pixtuoid-scene; one (Transport, AgentEvent) channel)
and .github/instructions/rust.instructions.md. Run just preflight (or at least
cargo nextest run --workspace) before the PR.
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.
- today First seen · 61 lines · 13 tokens per session scan A d562d56f12aa
add-source is a command published in the GitHub repository IvanWng97/pixtuoid (469 stars, last pushed yesterday), licensed MIT. It adds 13 tokens to every session and 1,015 once invoked, about $0.0001 per session on Opus 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 2026-09-06.
Other commands, from other repositories
monitor-fleet
Put every machine's claude-monitor on one page (discovers monitors, opens SSH tunnels, serves a switcher).
jdi-handoff
Hand this session off to an unattended agent-jdi run (quits it, then resumes in the background).
simplicio
Run the next user task through the simplicio-prompt Tuple-Space + Yool safe-speed runtime.
simplicio-install
Install the simplicio-prompt runtime contract into the current repository's agent rules files (CLAUDE.md, AGENTS.md, .cursorrules, .github/copilot-instructions.md, etc.).
simplicio-status
Toggle the simplicio-prompt opt-in status output ([Tuple Space Snapshot] / [Active] / [Total] / [Next Yool] / [Partial Result]).
check
Audit a .nika.yaml workflow before it runs — findings with their NIKA-XXXX codes, cost envelope, permits.