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/chankov/agent-fleetWrote 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/chankov/agent-fleet/assess-change-impact)<a href="https://agentmods.dev/commands/chankov/agent-fleet/assess-change-impact"><img src="https://agentmods.dev/badge/commands/chankov/agent-fleet/assess-change-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/chankov/agent-fleet/assess-change-impact"><img src="https://agentmods.dev/badge/commands/chankov/agent-fleet/assess-change-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 | $0.00000 | $0.00354 |
| Opus 5.5 | $0.00000 | $0.00142 |
| Sonnet 5.5 | $0.00000 | $0.00071 |
| Haiku 4.5 | $0.00000 | $0.00035 |
Grade A, and why
assess-change-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 20d 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
Command: Assess change impact
Use when a change needs an evidence-backed list of affected areas and verification priorities. Inputs: requested change or pending diff; optional ref/range if supported by the target VCS. An invocation does not authorize writes or external actions.
Process
- Read the target
.ai/rules/README.md, applicable boundary rule, and relevant existing documentation. For a future change with no diff, identify the proposed interfaces and likely owners; do not fabricate changed files. - Establish the affected files from the requested scope or actual diff. Trace inbound consumers via the target's real imports, callers, event subscriptions, interfaces or deployed entry points. Follow concrete links, not filenames alone.
- Classify each impact as direct, indirect or unmapped; note evidence and limits. Map to user-facing or operational entry points only where they exist. Do not presume an SPA, router, HTTP controller, language prefix or a specific client.
- Identify the target's actual checks and a short prioritized verification list. If asked to turn the analysis into a project requirements document, use the adapted project-task prompt in the target
.ai/agent-prompts/index by reference, not by copying it into this command.
Decision points
Ask with a recommendation when competing ownership or verification choices cannot be resolved from accepted target policy. An observed pattern alone does not authorize a new normative boundary.
Output and done when
Report scope, file/consumer-to-entry-point traces with evidence, direct/indirect/unmapped confidence, and prioritized checks. Explicitly list unknown consumers. No route or endpoint is reported as confirmed without a real reference.
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.
- 20d ago First seen · 20 lines · 0 tokens per session scan A 2a3555b125a8
assess-change-impact is a command published in the GitHub repository chankov/agent-fleet (19 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 354 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 2026-09-27.
Other commands, from other repositories
refactor
Systematic code refactoring with smart scope detection.
review-branch
Review the current branch's diff against base by dispatching atomic-reviewer. No orchestration loop, no spec required — pre-flight before /commit pr or /commit merge.
init
Install the formatters this repository needs, with every command visible before it runs.
merge-conflict-analysis
You are analyzing merge conflicts for PR #${{ pr-number }}.
boot
Start a new PromptKit prompt assembly session (alias for /bootstrap).
repo-audit
Audit a codebase (local or remote GitHub/GitLab) against architecture principles and requirements, surfacing drift, risk, and missing decisions.