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 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/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/soulcodex/agentic/persist-plan"><img src="https://agentmods.dev/badge/skills/soulcodex/agentic/persist-plan.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00092 | $0.01008 |
| Opus 5.5 | $0.00037 | $0.00403 |
| Sonnet 5.5 | $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 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.
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.
- 1mo 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 today), licensed MIT. It adds 92 tokens to every session and 1,008 once invoked, about $0.0004 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
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.
batch
Execute batch operations on multiple files in parallel. Automatically discovers files, splits into chunks, and processes with parallel worker agents. Use /batch followed by operation and file pattern. For many independent single-turn transforms (translate/rewrite/extract each file into a new file) that can wait…
batch-api
Prepare a many-file, single-turn transform (translate, rewrite, extract) as a plan and submit it to the asynchronous, half-price DashScope Batch API; results are delivered as new files hours later. Invoke explicitly with /batch-api.
loop
Create a loop that runs a prompt now and follows up either on a fixed schedule or through self-paced wakeups. Usage - /loop check the build, /loop 5m check the build, /loop check the PR every 30m. /loop list to show jobs, /loop clear to cancel all.
slackcli
Read, send, search, and manage Slack workspaces with the slackcli binary. Installs slackcli if missing and checks or proposes authentication first. Use whenever the user mentions Slack or pastes a slack.com link.
termio
See and drive the sibling agent sessions running alongside you in this Termio project via the termio sessions CLI — list and watch their status, spawn new agent or plain-terminal sessions, send a prompt or an answer into a session, and read an agent's reply from its transcript. Use when delegating work to another…