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 plan-featuregit 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/plan-feature)<a href="https://agentmods.dev/skills/karthick-ramachandran/persist-os/plan-feature"><img src="https://agentmods.dev/badge/skills/karthick-ramachandran/persist-os/plan-feature/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/plan-feature"><img src="https://agentmods.dev/badge/skills/karthick-ramachandran/persist-os/plan-feature.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 | $0.00050 | $0.00384 |
| Opus 5.5 | $0.00020 | $0.00154 |
| Sonnet 5.5 | $0.00010 | $0.00077 |
| Haiku 4.5 | $0.00005 | $0.00038 |
Grade A, and why
plan-feature 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 1mo 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
Goal
Turn approved requirements into an ordered implementation plan without writing implementation code.
Inputs
- Approved requirements or feature PRD.
- Acceptance criteria.
- Known constraints or release target.
Workflow
- Restate the objective and acceptance criteria in one paragraph.
- Identify the affected modules, docs, templates, and tests.
- Record architecture impact and whether a new ADR is needed (propose it; never accept it yourself).
- Break the work into ordered tasks, each with explicit completion evidence.
- Derive the test plan from acceptance criteria, risks, and likely regressions.
- Stop before implementation and hand back the PLAN, TASKS, and TEST_PLAN paths.
Decisions
- If requirements are missing or contradictory → stop and ask for them.
- If a task would change accepted non-goals → stop and ask for approval.
- If the request is a small local fix → skip this skill and implement directly with focused tests.
Verification
- PLAN.md states the objective, scope, and architecture impact.
- Every task maps to an acceptance criterion or a stated risk.
- No implementation code was written.
Resources
- For completion evidence rules → docs/50-quality/QUALITY_GATES.md
- For engineering rules → docs/60-engineering/ENGINEERING_STANDARDS.md
- For sensitive scope → docs/20-security/SECURITY_MODEL.md
- For prior decisions → docs/adrs/
Output
- Paths of the PLAN.md, TASKS.md, and TEST_PLAN.md files written.
- One-paragraph summary of scope and the recommended first task.
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.
- 1mo ago Changed · -19 lines · +5 tokens per session c211f6ed9a1a
- 2mo ago First seen · 68 lines · 45 tokens per session scan A 598b0d78c06b
plan-feature is a skill published in the GitHub repository Karthick-Ramachandran/persist-os (9 stars, last pushed 16d ago), licensed MIT. It adds 50 tokens to every session and 384 once invoked, about $0.0002 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 2026-08-31.
Other skills, from other repositories
actual
Feature-complete companion for the actual CLI, an ADR-powered CLAUDE.md/AGENTS.md generator. Runs and troubleshoots actual adr-bot, status, auth, config, runners, and models, plus the Actual AI platform surface: login, logout, whoami, and advisor (org-scoped architecture Q&A). Covers all 5 runners (claude-cli…
index-atlas
Run ContextAtlas extraction inside Claude Code session (subscription-bounded; no Anthropic API key needed). Walks ADRs + source-symbol docstrings + filtered commit messages via contextatlas list-extraction-sources and extracts architectural claims via per-source iteration discipline. Persists to…
generate-adrs
Generate Architectural Decision Records (ADRs) for a codebase by walking the source tree, identifying non-obvious architectural decisions, and writing canonical ContextAtlas-format ADRs to docs/adr/. Runs inside Claude Code session (subscription-bounded; no Anthropic API key needed). Supports optional…
refresh-atlas
Tier 1 incremental claim refresh for ContextAtlas. Re-extracts claims for the sources in the pending queue only (changed ADRs, changed docstring files, new filtered commits), then runs the Skill-path gates. Runs headless through contextatlas refresh-claims (subscription-bounded; no API key) or by hand in a Claude Code…
evidence-anchors
Ground documents in verifiable citations. Use whenever writing or editing ANY document a human will approve or review that asserts something about the EXISTING codebase — a design doc, proposal, RFC, ADR, risk assessment, a PLAN (including plan mode), or a PR DESCRIPTION. Load-bearing claims must carry Evidence…
setup
Guided onboarding for nullius in this repo — detects test frameworks to propose Oracle config, offers the GitHub Action CI check, and walks through enabling the hook plugin. Use when a user asks to set up, install, enable, configure, or onboard nullius, or asks what nullius needs to be fully working here.