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/benizzio/spec-kit-coding-standards-drift-control/speckit.coding-standards-drift-control.reportgit clone --depth 1 https://github.com/benizzio/spec-kit-coding-standards-drift-controlWrote 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/benizzio/spec-kit-coding-standards-drift-control/speckit.coding-standards-drift-control.report)<a href="https://agentmods.dev/commands/benizzio/spec-kit-coding-standards-drift-control/speckit.coding-standards-drift-control.report"><img src="https://agentmods.dev/badge/commands/benizzio/spec-kit-coding-standards-drift-control/speckit.coding-standards-drift-control.report.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 | $0.00017 | $0.02172 |
| Opus 5 | $0.00009 | $0.01086 |
| Sonnet 5 | $0.00003 | $0.00434 |
| Haiku 4.5 | $0.00002 | $0.00217 |
Grade A, and why
speckit.coding-standards-drift-control.report 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 5d 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 — 156 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Generate Coding Standards Drift Report
Review the active feature implementation for divergences from the repository coding-standards baseline and write a structured drift report.
User Input
$ARGUMENTS
You MUST consider the user input before proceeding (if not empty). The user may narrow the review scope, request a full rerun, or ask to focus on specific files or existing drift IDs.
Purpose
- Focus on coding standards and software engineering practices only.
- Do not review domain correctness, product behavior, contract compliance, or feature completeness unless that context is required to explain a coding-standards drift.
- This command is rerunnable and incremental. Merge each new review into the existing report instead of replacing it: keep every prior finding section, preserve stable
CODE-STAND-DRIFT-###identifiers, append newly discovered findings asPending, and preserve existing finding statuses unless a resolved finding reappears and must be reopened toPending. If an existing report still uses legacyDRIFT-###identifiers, rewrite equivalent findings toCODE-STAND-DRIFT-###while preserving the numeric suffix. - Do not set any finding to
Resolved. Only the final status-update task generated by/speckit.coding-standards-drift-control.remediation-planmay change remediated findings toResolved. - Run only after the active feature's normal Spec Kit implementation tasks are complete.
Prerequisites
- Verify a Spec Kit project exists by checking for
.specify/. - Run
.specify/scripts/bash/check-prerequisites.sh --json --require-tasks --include-tasksfrom repo root and parse the absoluteFEATURE_DIR. - Verify
spec.md,plan.md, andtasks.mdexist inFEATURE_DIR. - Load the current Spec Kit task format references before interpreting task state:
.specify/templates/tasks-template.mdwhen present- the existing
FEATURE_DIR/tasks.md
- Using the task state syntax from the current local Spec Kit installation and the existing task file, verify there are no open, unchecked, pending, or reopened tasks in
FEATURE_DIR/tasks.md. If any are present, stop without writing the report and instruct the user to finish implementation with/speckit.implementbefore running drift control. - Discover and load
AGENTS.mdplus any other known proprietary agent-instruction files present in repository or feature scope, such asCLAUDE.md,GEMINI.md,.github/copilot-instructions.md,.cursorrules,.cursor/rules/**,.windsurfrules, or.clinerules. - Load
.specify/memory/constitution.mdif it exists. - If the loaded instructions and constitution do not enforce concrete coding standards or software engineering practices, derive the best-guess baseline conservatively from the existing code style, structure, documentation patterns, and architectural boundaries in the active feature scope and directly related code.
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.
- 5d ago First seen · 156 lines · 17 tokens per session scan A 31e067aa2efa
speckit.coding-standards-drift-control.report is a command published in the GitHub repository benizzio/spec-kit-coding-standards-drift-control (2 stars, last pushed 2mo ago), licensed MIT. It adds 17 tokens to every session and 2,172 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 2026-08-31.
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.
constitution
Create or update the project constitution from interactive or provided principle inputs.
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.