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/aahlijia/dekkoWrote 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/aahlijia/dekko/impact)<a href="https://agentmods.dev/commands/aahlijia/dekko/impact"><img src="https://agentmods.dev/badge/commands/aahlijia/dekko/impact/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/aahlijia/dekko/impact"><img src="https://agentmods.dev/badge/commands/aahlijia/dekko/impact.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 | $0.00013 | $0.00607 |
| Opus 5.5 | $0.00005 | $0.00243 |
| Sonnet 5.5 | $0.00003 | $0.00121 |
| Haiku 4.5 | $0.00001 | $0.00061 |
Grade A, and why
impact 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 19d 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 — 49 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Impacted tests
!dekko affected $ARGUMENTS
Your task
The report above was generated programmatically by dekko affected
(reverse call-graph reachability from the changed symbols, plus an
import-edge fallback). Do NOT re-derive it by grepping test files for
the changed names.
- Relay the headline (
N impacted test files vs REV) and the files grouped by the tier tag printed in brackets:[direct]calls changed code itself,[transitive]reaches it through the call graph,[import]only imports a changed file. Name one or two of the impacted symbols per file where that helps the user see why. - The line(s) after the list that start with a test runner
(
pytest ...,cargo test ...,go test ..., the repo'spackage.jsontest script,./gradlew ...,mvn ...) are the ready-to-run command. Show them verbatim in a code block. If the user asked to run the tests, run that command; otherwise offer to. - If a runner line ends with
# +N more impacted test files not shown; --budget 0 lists all, the report was budget-capped and the command is incomplete. Rerundekko affected $ARGUMENTS --budget 0and take the command from that output before running anything. If that lists hundreds of files, say so: running the whole suite is often the saner call, and on Windows a command line that long won't start. no impacted tests vs REVmeans no changed callable reaches a test file. Say so plainly. If the user expected a change to show, the default REV is the commit the map was generated at (elseHEAD), so a change already committed needs an older base: suggest/impact <base-branch>or/impact HEAD~N.- A
note:counting tests that reach the change only through an ambiguous call: relay the count as "may also be impacted" and say that/impact REV --possiblelists them, nearest the changed code first. They never join the command line. - An error naming the rev (
cannot export git rev ...) means an unknown rev or not a git repo: relay it and ask for a valid rev. - These are leads, not verdicts: static analysis misses fixtures and
dynamic dispatch. If the list looks thin for the size of the
change, say that and point at the
dekko-verifyskill.
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.
- 19d ago First seen · 49 lines · 13 tokens per session scan A 5986df317f43
impact is a command published in the GitHub repository aahlijia/dekko (5 stars, last pushed yesterday), licensed MIT. It adds 13 tokens to every session and 607 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 2026-09-27.
Other commands, from other repositories
codeweb-apply
Execute the codeweb consolidation campaign's READY tier step-by-step — simulate, apply, refresh, diff-gate, test, commit (or revert and record blocked). The deterministic gate owns every verdict; this command only drives the loop.
fidelity
Measure how faithfully a clone reproduces a site — pixel-diff plus motion-fidelity into one 0-100 score, a letter grade, a ranked correction plan, and a shareable card.
feature-implement-execute
Phase 4 of develop: Execute the implementation plan with per-task TDD, quality gates, and completion verification.
audit-mirage-analyze
Phases 2-3 and 7 of auditing-green-mirage: systematic line-by-line audit, the Green Mirage Patterns, named assertion shapes, and the fix-verification Test Adversary prompt.
pr-dance
Loop a PR through CI and bot review until merge-ready. Use when user says '/pr-dance', 'do the PR dance', or finishing-a-development-branch dispatches option 3.
loop
Autonomous execution loop. Runs the TDD cycle repeatedly until all tasks in an epic are complete, with circuit breaker protection and PR workflow.