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 skills add Karthick-Ramachandran/persist-os --skill architecture-drift-reviewgit clone --depth 1 https://github.com/Karthick-Ramachandran/persist-osWrote 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/skills/karthick-ramachandran/persist-os/architecture-drift-review)<a href="https://agentmods.dev/skills/karthick-ramachandran/persist-os/architecture-drift-review"><img src="https://agentmods.dev/badge/skills/karthick-ramachandran/persist-os/architecture-drift-review/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/skills/karthick-ramachandran/persist-os/architecture-drift-review"><img src="https://agentmods.dev/badge/skills/karthick-ramachandran/persist-os/architecture-drift-review.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 | $0.00037 | $0.00453 |
| Opus 5 | $0.00018 | $0.00227 |
| Sonnet 5 | $0.00007 | $0.00091 |
| Haiku 4.5 | $0.00004 | $0.00045 |
Grade A, and why
architecture-drift-review 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 12d 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
Skill: Architecture Drift Review
Purpose
Find changes that diverge from accepted repository memory.
Drift is not difference from a Persist OS recommendation. Persist OS is architecture-neutral.
Inputs
- Change summary or diff.
- Feature docs.
- Module docs.
- ADRs.
- Test results.
Required Reading
docs/10-architecture/ARCHITECTURE.mddocs/60-engineering/ENGINEERING_STANDARDS.mddocs/20-security/SECURITY_MODEL.md- Relevant
docs/30-modules/<module>/MODULE.md - Relevant
docs/40-features/<feature>/PRD.md - Relevant
docs/adrs/*.md
Output Files
- Relevant feature
REVIEW.md - Relevant feature
COMPLETION_REPORT.md - Updated docs only when the human accepts documented evolution.
Process
- Review the change and identify changed modules and generated outputs.
- Compare changes against accepted ADRs and repository decisions.
- Compare changes against module boundaries.
- Check for new dependencies and security-sensitive changes.
- Check whether tests and docs were updated.
- Classify findings.
Finding Types
- Architecture drift
- Dependency drift
- Module drift
- Security drift
- Testing drift
- Documentation drift
- Engineering standards drift
- Acceptable documented evolution
Stop Conditions
Stop and request human decision if:
- An accepted ADR conflicts with the implementation.
- The implementation conflicts with engineering standards.
- A dependency was added without ADR consideration.
- Authentication, authorization, storage, networking, secrets, telemetry, cloud, runtime MCP, or file write behavior changed without security review.
- Feature behavior changed without a PRD or change request update.
Quality Bar
- Findings distinguish drift from documented evolution.
- Findings compare against accepted repository memory, not Persist OS preferences.
- Each blocker names the missing source-of-truth update.
- Review output is concrete enough to act on.
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.
- 12d ago First seen · 76 lines · 37 tokens per session scan A 60fff5ba2dcf
architecture-drift-review is a skill published in the GitHub repository Karthick-Ramachandran/persist-os (8 stars, last pushed 2mo ago), licensed MIT. It adds 37 tokens to every session and 453 once invoked, about $0.0002 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 skills, from other repositories
architecture-governance
Keep code changes conformant to a repo's real, declared architecture using ArchSteer. Use when starting work in an unfamiliar repo, before finishing/committing an architecturally significant change (new dependency, new data access, new external call, new layer), or when asked about a codebase's architecture, layers…
cn-check
Install and run the Continue CLI (cn) to execute AI agent checks on local code changes. Use when asked to "run checks", "lint with AI", "review my changes with cn", or set up Continue CI locally.
review
Validate plans, execution, or PRs against wish criteria — returns SHIP / FIX-FIRST / BLOCKED with severity-tagged gaps.
openlore-execute-refactor
Apply a confirmed .openlore/refactor-plan.md with a test gate after each change. Use when asked to execute or continue an OpenLore refactoring plan.
review
Adversarial fresh-context review of an increment before it ships. Every finding cites path:line and is re-verified. Use when saying "review", "grill this", or "critique the implementation".
genie-orca-review
Independent, read-only review of a group, a wish, or a PR on Orca — SHIP / FIX-FIRST / BLOCKED with severity-tagged findings. Council and retro are this skill with a different input.