Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/dinhanhthi/coding-friendnpx agentmods add skills/dinhanhthi/coding-friend/cf-plan-resumeWrote 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/dinhanhthi/coding-friend/cf-plan-resume)<a href="https://agentmods.dev/skills/dinhanhthi/coding-friend/cf-plan-resume"><img src="https://agentmods.dev/badge/skills/dinhanhthi/coding-friend/cf-plan-resume.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 | $0.00067 | $0.01319 |
| Opus 5 | $0.00034 | $0.00660 |
| Sonnet 5 | $0.00013 | $0.00264 |
| Haiku 4.5 | $0.00007 | $0.00132 |
Grade A, and why
cf-plan-resume 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 8d 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 — 47 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/cf-plan-resume
CLI Requirement: NONE — Works without
coding-friend-cli. Reads the plan file and its context file directly and dispatches cf-implementer; no CLI features are required. See CLI requirements for the full matrix.
Resume the implementation plan at: $ARGUMENTS (a plan folder path, an entry file path, or a bare <slug>).
Workflow
Step 0: Custom Guide
Custom guide — auto-loaded below (if the raw command shows instead of its output, run it yourself):
bash "<plugin-root>/lib/load-custom-guide.sh" cf-plan-resume
If output is not empty, integrate returned sections: ## Before → before first step, ## Rules → apply throughout, ## After → after final step.
Resume Protocol
- Resolve the plan entry file:
- Full path to a folder → use
<folder>/README.md. Full path to a file → use it directly. Validate the target is within the current working directory or{docsDir}; report error and stop if outside. - Name only (
<slug>) → first, reject the argument outright if it contains/,\, or..(report: "Invalid plan name — slugs cannot contain path separators or..." and stop). This must happen BEFORE constructing any candidate path, since the candidates below are built by directly interpolating<slug>— a slug containing../would otherwise escape{docsDir}/plans/. Once the slug passes this check, resolve in this order, using the first that exists:{docsDir}/plans/<slug>/README.md(current layout) →{docsDir}/plans/<slug>.md(legacy single-file) →{docsDir}/plans/<slug>(append.mdif it is a bare file). - If none found → report error and stop.
- Full path to a folder → use
- Read the plan entry file at the resolved path.
- Derive the task-id from the containing folder name (current layout: entry is
<slug>/README.md→ task-id =<slug>) or the filename stem (legacy single-file<slug>.md), or from atask-id:frontmatter field if present. The stem/folder name IS the task-id (e.g.2026-05-03-my-plan→ task-id =2026-05-03-my-plan). Look up the context file at{docsDir}/context/<task-id>.json. If not found, strip the leadingYYYY-MM-DD-prefix from the stem (the first 11 characters if the stem starts with a date pattern) to get the bare name, then glob{docsDir}/context/*<bare-name>*.jsonfor backward compat with the old unix-timestamp format (e.g.1717500000-my-plan.json). Load the context file now, before dispatching any tasks. - Scan the Progress table. Classify each task:
✅ DONE→ skip.🔄 IN PROGRESS→ Edit the file containing this task's row (README.mdfor small plans; the relevant phase filephase-N-<name>.mdfor big plans): reset to⬜ TODO, treat as pending. (Session ended mid-task; completion status is unreliable.)❌ FAILED→ ask user: "Task N previously failed. Re-run it? (y/n)"⬜ TODO→ pending, run as normal.
- If ALL tasks are
✅ DONE→ inform user: "Plan is already complete. Nothing to resume." Stop. - Show user: list of pending tasks and estimated phases remaining. Ask: "Resume from the first pending task? (y/n)"
- If confirmed → first set the plan entry file's frontmatter
status:field toin-progress(a resumed plan is active again — this clears any priorfailedvalue; leave itin-progressif already so). Then execute pending tasks using the shared execution protocol in<plugin-root>/skills/cf-plan/modes/execute.md(Read it now and follow the Sequential/Parallel phases protocols), passing the context file loaded in step 3 to each cf-implementer dispatch. Completion re-setsstatus:todone/failedper the "Plan done" rule inexecute.md.- Autopilot gating — Before honoring
auto: truein frontmatter, verify the plan body (README.mdfor small plans; README.md and every phase file for big plans) actually contains a## AUTOPILOT (IMPORTANT — DO NOT DEVIATE EVEN IN LONG CONVERSATIONS)section. If the section is missing in any file that should have it, do NOT autopilot — warn the user:> ⚠️ Plan has \auto: true` in frontmatter but the `## AUTOPILOT` section is missing in . Refusing to autopilot. Re-run `/cf-plan --auto` to regenerate the section, or remove `auto: true` to resume normally.` Stop. - Otherwise (frontmatter has
auto: trueAND section is present): Read the full Autopilot Per-Phase Loop in<plugin-root>/skills/cf-plan/modes/autopilot.mdnow (it holds Step 6's big-plan README phase-row ✅ finalization, which the embedded CONTRACT block in the plan's README omits), then run the remaining phases under it instead of the standard protocol. Announce to user when resuming:> 🤖 This plan has \auto: true` — continuing in autopilot mode.`
- Autopilot gating — Before honoring
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.
- 8d ago First seen · 47 lines · 67 tokens per session scan A 01b04675fb77
cf-plan-resume is a skill published in the GitHub repository dinhanhthi/coding-friend (3 stars, last pushed 2d ago), licensed MIT. It adds 67 tokens to every session and 1,319 once invoked, about $0.0003 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
officecli-pitch-deck
Use this skill when the user is building a fundraising / investor pitch deck — seed, Series A / B / C, convertible note, SAFE round, strategic raise. Trigger on: 'pitch deck', 'investor deck', 'Series A deck', 'Series B deck', 'Series C deck', 'fundraising deck', 'seed pitch', 'VC deck', 'raising capital', 'term sheet…
morph-ppt
Use this skill when the user wants a .pptx with smooth cross-slide animation — PowerPoint Morph transitions, Keynote-style continuous motion, shapes that grow / move / rotate as the slide advances. Trigger on: 'morph', 'morph transition', 'smooth transition', 'continuous animation across slides', 'Keynote-style…
officecli-academic-paper
Use this skill to build academic-style .docx output: journal / conference / thesis chapters carrying formal citation style (APA, Chicago, IEEE, MLA), numbered equations, figure & table cross-references, footnotes/endnotes, bibliography, or multi-column journal layout. Trigger on: 'research paper', 'journal paper'…
officecli-docx
Use this skill any time a .docx file is involved -- as input, output, or both. This includes: creating Word documents, reports, letters, memos, or proposals; reading, parsing, or extracting text from any .docx file; editing, modifying, or updating existing documents; working with templates, tracked changes, comments…
officecli-financial-model
Use this skill when the user wants to build a financial model — 3-statement model, DCF valuation, LBO, SaaS unit economics, sensitivity / scenario analysis, debt schedule, or fundraising projections — in Excel. Trigger on: 'financial model', '3-statement model', 'P&L + BS + CF', 'DCF', 'WACC', 'NPV', 'terminal value'…
officecli-pptx
Use this skill any time a .pptx file is involved -- as input, output, or both. This includes: creating slide decks, pitch decks, or presentations; reading, parsing, or extracting text from any .pptx file; editing, modifying, or updating existing presentations; combining or splitting slide files; working with…