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 skills/soulcodex/agentic/persist-plannpx skills add soulcodex/agentic --skill persist-plangit clone --depth 1 https://github.com/soulcodex/agenticWrote 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/soulcodex/agentic/persist-plan)<a href="https://agentmods.dev/skills/soulcodex/agentic/persist-plan"><img src="https://agentmods.dev/badge/skills/soulcodex/agentic/persist-plan.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 | $0.00092 | $0.01008 |
| Opus 5 | $0.00046 | $0.00504 |
| Sonnet 5 | $0.00018 | $0.00202 |
| Haiku 4.5 | $0.00009 | $0.00101 |
Grade A, and why
persist-plan 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 4d 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 — 140 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Persist Plan Skill
Capture a plan or architectural decision as a discoverable, structured file so that any agent or team member can find it later without re-deriving the context.
When planning directly against a GitHub issue, use github-issue-planning for
issue-backed plan persistence on GitHub (prefer MCP, fallback to gh CLI).
Use this skill for local .agentic/plans/ persistence.
Step 1 — Gather Plan Metadata
Collect (or confirm) the following before writing:
- Title — a short, descriptive phrase (e.g., "Introduce CQRS in order service", "Migrate auth to hexagonal ports"). Used for the filename and H1 heading.
- Type — one of:
feature,refactor,architecture,investigation,decision. - Status — one of:
draft,in-progress,completed,superseded. - Affected areas — which modules, bounded contexts, or services does this plan touch?
- Author — the agent name or human handle that produced the plan.
Step 2 — Derive the Filename
Build the filename as:
YYYY-MM-DD-{kebab-case-title}.md
Examples:
2026-03-06-introduce-cqrs-in-order-service.md
2026-03-06-migrate-auth-to-hexagonal-ports.md
- Use today's date in
YYYY-MM-DDformat. - Slugify the title: lowercase, replace spaces and special characters with hyphens, strip leading/trailing hyphens.
- If a file with the same slug already exists for today, append
-2,-3, etc.
Step 3 — Write the Plan File
Save to .agentic/plans/{filename} using the template from plan-template.md.
Mandatory sections:
# {Title}
**Date**: YYYY-MM-DD
**Type**: feature | refactor | architecture | investigation | decision
**Status**: draft | in-progress | completed | superseded
**Affected**: [list of modules / bounded contexts / services]
**Author**: {agent-name or handle}
## Context
What situation, problem, or question prompted this plan?
Be specific — a reader unfamiliar with the moment must understand the trigger.
## Goals
What does this plan aim to achieve?
Use bullet points. Each goal must be verifiable (done / not done).
## Approach
How will the goals be achieved?
Include the key decisions made, alternatives considered, and the rationale for
the chosen direction. Reference relevant fragments, ADRs, or tickets where applicable.
## Steps
Ordered list of concrete tasks derived from this plan.
1. ...
2. ...
## Risks & Open Questions
- Any unknowns, blockers, or decisions that still need to be made.
## Outcome
(Fill in when status moves to `completed` or `superseded`.)
What was the actual result? Did the plan change during execution? Why?
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 4d ago First seen · 140 lines · 92 tokens per session scan A 93189acb2089
persist-plan is a skill published in the GitHub repository soulcodex/agentic (10 stars, last pushed 4d ago), licensed MIT. It adds 92 tokens to every session and 1,008 once invoked, about $0.0005 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
sparc-methodology
SPARC (Specification, Pseudocode, Architecture, Refinement, Completion) development methodology with multi-agent orchestration. Use when running a structured spec-to-code workflow or decomposing a feature through the SPARC phases.
design-debt-audit
Inventory and prioritise accumulated design inconsistencies across a product. Use when drift has built up over time. For token coverage specifically use design-token-audit (designer-toolkit); for WCAG gaps use accessibility-audit (design-systems).
design-impact-reporting
Communicate design's contribution to business and user outcomes in stakeholder language. Use when reporting results upward. For choosing the metrics in the first place, use metrics-definition (ux-strategy).
research-repository
Build a repository that makes findings findable, reusable, and cumulative across teams. Use when the same research keeps getting redone. For synthesising one study, use affinity-diagram.
survey-design
Design unbiased survey instruments — question wording, scales, and sampling — to measure attitudes at scale. Use when you need quantitative breadth. For behavioural experiments, use a-b-test-design (prototyping-testing).
localization-design
Design for multiple languages, writing directions, and cultural contexts — text expansion, RTL mirroring, and locale formats. Use when shipping beyond one locale. For the words themselves, use ux-writing (designer-toolkit).