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/omrikais/cctally/dashboard-perfgit clone --depth 1 https://github.com/omrikais/cctallyWrote 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/omrikais/cctally/dashboard-perf)<a href="https://agentmods.dev/commands/omrikais/cctally/dashboard-perf"><img src="https://agentmods.dev/badge/commands/omrikais/cctally/dashboard-perf.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 | $0.00000 | $0.03092 |
| Opus 5 | $0.00000 | $0.01546 |
| Sonnet 5 | $0.00000 | $0.00618 |
| Haiku 4.5 | $0.00000 | $0.00309 |
Grade A, and why
dashboard-perf 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.
How it starts
The opening of the file, as written. The whole thing — 241 lines — stays where its author put it; the contents beside it link to each section on GitHub.
cctally dashboard-perf
Read a running dashboard's tick cost, and arm or disarm its deep phase trace.
Answers the question "why is my dashboard slow, and how slow is it?" from the
running process — no restart, and no CCTALLY_PERF_TRACE=1 at launch.
Restarting to answer that question does not work: it discards both the accumulated memos and the condition being diagnosed. So the counters this command reads are always on, and the deeper phase trace is armed at runtime.
Modes
| Mode | What it does |
|---|---|
cctally dashboard-perf |
Human-readable report from a running dashboard |
cctally dashboard-perf --json |
Machine-readable JSON to stdout (schemaVersion: 1) |
cctally dashboard-perf --trace on |
Arm the deep phase trace, then report |
cctally dashboard-perf --trace off |
Disarm the deep phase trace, then report |
Flags
| Flag | Default | Meaning |
|---|---|---|
--host HOST |
127.0.0.1 |
Loopback IP literal of the running dashboard |
--port PORT |
the cctally dashboard default |
Port of the running dashboard |
--token TOKEN |
none | Bearer token, when the dashboard minted one for LAN access |
--trace {on,off} |
none | Arm or disarm the deep phase trace on the running process |
--json |
off | Emit the stamped JSON envelope instead of the report |
--host accepts only an IP literal in 127/8 or ::1. A hostname is refused
at argument validation, localhost included, and the command exits 2 without
opening a connection.
This is stricter than the server, deliberately. The endpoint's
anti-rebinding gate treats localhost and ::1 as loopback names before it
tries to parse an IP literal, so Host: localhost:8789 is served with 200. The
command refuses a name anyway: a name is resolved by the operating system, the
CLI cannot verify that the resolver's answer is this machine, and an
unambiguous target is worth more here than the convenience. A hostname that is
not a loopback name, such as evil.example.com, is refused by the server too.
The command never contacts a LAN address.
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 Changed · +32 lines 8ac6db385acc
- 5d ago First seen · 209 lines · 0 tokens per session scan A 3571dee84dd4
dashboard-perf is a command published in the GitHub repository omrikais/cctally (5 stars, last pushed yesterday), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 3,092 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 2026-08-31.
Other commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.