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 implement-taskgit 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/implement-task)<a href="https://agentmods.dev/skills/karthick-ramachandran/persist-os/implement-task"><img src="https://agentmods.dev/badge/skills/karthick-ramachandran/persist-os/implement-task.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 | $0.00037 | $0.00398 |
| Opus 5 | $0.00018 | $0.00199 |
| Sonnet 5 | $0.00007 | $0.00080 |
| Haiku 4.5 | $0.00004 | $0.00040 |
Grade A, and why
implement-task 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 6d 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: Implement Task
Purpose
Implement a bounded task safely from approved requirements and plans.
Inputs
- Task description.
- Feature plan or acceptance criteria.
- Relevant module and architecture docs.
Required Reading
AGENTS.mddocs/10-architecture/ARCHITECTURE.mddocs/10-architecture/FILE_WRITE_POLICY.mddocs/20-security/SECURITY_MODEL.mddocs/60-engineering/ENGINEERING_STANDARDS.md- Relevant feature, module, and ADR docs.
Output Files
- Implementation files for the scoped task.
- Tests for changed behavior.
- Updated module, feature, or completion docs when behavior changes.
Process
- Confirm the task has clear acceptance criteria.
- Confirm the task comes after PRD, acceptance, architecture impact, and test plan.
- Identify affected modules and tests.
- Implement the smallest safe change.
- Add or update tests based on risk.
- Update docs when behavior, architecture, or module ownership changes.
- Prepare completion evidence with commands and results.
Stop Conditions
Stop and request human decision if:
- The task conflicts with source-of-truth docs.
- The task conflicts with engineering standards.
- The task requires adding runtime network, telemetry, cloud, MCP, AI API, or generated production app behavior without review.
- A dependency is needed without ADR consideration.
- Tests cannot be designed from the available requirements.
Quality Bar
- Scope stays narrow.
- Tests cover behavior and risk.
- File write and security rules are preserved.
- Engineering standards are followed.
- Completion evidence is concrete.
- One task is implemented at a time.
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.
- 6d ago First seen · 65 lines · 37 tokens per session scan A 2e81823db107
implement-task 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 398 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
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…
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…
rework-rate
Measure and interpret PR rework rate — the emerging 5th DORA metric.
work
Execute an approved wish plan — orchestrate subagents per task group with fix loops, validation, and review handoff.
openlore-brainstorm
Transform a feature idea into an annotated story using a Domain Sketch or Constrained Option Tree. Use when asked to brainstorm, explore, or shape a feature before implementation.
trace
Dispatch trace subagent to investigate unknown issues — reproduces, traces, and reports root cause for fix handoff.