What is wtfp-resume-writing?

A writing-project resume workflow that restores the latest saved handoff and identifies the next safe action. A handoff is a record of where work stopped and what should happen next.

Use it to continue an academic writing or research project from its saved state, including sections, reviews, checkpoints, and validations.

It reduces the need to reconstruct project status from scattered notes after an interruption or change of session.

wtfp-resume-writing — Skill for Claude Code by akougkas/wtf-p

Install

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.

Any agent

npx skills add akougkas/wtf-p --skill wtfp-resume-writing

Clone the repo

git clone --depth 1 https://github.com/akougkas/wtf-p

Made for: Claude Code.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/akougkas/wtf-p/wtfp-resume-writing/github.svg)](https://agentmods.dev/skills/akougkas/wtf-p/wtfp-resume-writing)

Your own site

<a href="https://agentmods.dev/skills/akougkas/wtf-p/wtfp-resume-writing"><img src="https://agentmods.dev/badge/skills/akougkas/wtf-p/wtfp-resume-writing/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/akougkas/wtf-p/wtfp-resume-writing"><img src="https://agentmods.dev/badge/skills/akougkas/wtf-p/wtfp-resume-writing.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 22 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,010 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00022	$0.01010
Opus 5.5	$0.00009	$0.00404
Sonnet 5.5	$0.00004	$0.00202
Haiku 4.5	$0.00002	$0.00101

Measured 3d ago against content hash c0c39c5f3d20, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

wtfp-resume-writing 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 3d 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.

vendors/antigravity/skills/wtfp-resume-writing/SKILL.md · 74 lines

How it starts

The opening of the file, as written. The whole thing — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Resume writing

@${PLUGIN_ROOT}/project/README.md @${PLUGIN_ROOT}/skills/wtfp-manage-project/SKILL.md @${PLUGIN_ROOT}/skills/wtfp-manage-project/references/actions.md

Record contract

Read: project://manifest, project://config, project://state, project://decisions, project://structure/outline, project://checkpoints/{checkpoint}, project://sections/{section}, project://sections/{section}/plans/{plan}, project://sections/{section}/reviews/{review}, project://sections/{section}/handoff, project://sections/{section}/summary, project://validations/{validation}, project://paper/{artifact}. Produce: project://checkpoints/{checkpoint} (update), project://state (update).

Resolve every logical URI through the host adapter. Portable v1 JSON records are the source of truth: schema-validate before a write, preserve stable IDs, update revision and timestamps where required, and replace records atomically. Never pass a literal logical URI to a shell command or infer record state from a legacy Markdown control file.

Manuscript prose and supporting context, research, plan, review, summary, handoff, and deliverable artifacts retain their authored format (normally Markdown). Link them from the relevant v1 record; do not convert manuscript prose into project-state JSON.

Procedure

In the current invocation, read and schema-validate the manifest, config, state, decisions, and every pending active checkpoint. Read the chosen pending checkpoint plus its linked handoff, section, selected plan, reviews, validations, manuscript, summary, and outline; a prior conversation, invocation prose, or generated report is not evidence that these reads occurred. Missing, stale, ambiguous, or conflicting resume inputs fail closed with zero writes.
Verify referenced revisions and artifacts are current, then report completed work, pending work, blockers, stale assumptions, and the exact bounded options. Do not create a report artifact: before selection the action is read-only.
Invoke the host's interactive user gate and wait for one exact option. Invocation arguments may request resumption but cannot answer this gate. If the gate is unavailable or no response is returned, report needs-input and make no mutation.
Only after the returned selection, resolve, waive, or expire the checkpoint as selected and set state.status to active when continuation is confirmed. Preserve the existing valid state.phase, increment required revisions, and clear only the resolved active checkpoint URI.
Schema-validate and read back checkpoint and state before claiming success. Preserve the handoff until the selected continuation itself is confirmed.

Read the full file on GitHub · 74 lines

Changes

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.

3d ago First seen · 74 lines · 22 tokens per session scan A c0c39c5f3d20

Subscribe to this mod's changes

wtfp-resume-writing is a skill published in the GitHub repository akougkas/wtf-p (20 stars, last pushed 4d ago), licensed MIT. It adds 22 tokens to every session and 1,010 once invoked, about $0.0001 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 2026-11-10.

Research Writing and docs academic-paper agentic-ai ai-agents gemini-cli opencode

wtfp-resume-writing next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
wtfp-resume-writingakougkas/wtf-p	Skill	20	4d ago	MIT	A	22	Claude Code
install-gemini-code-review-actionderailed-dash/dazbo-agent-skills	Skill	28	yesterday	MIT	A	73	Claude Code, Codex
showagent-session-handoffaytzey/showagent	Skill	63	yesterday	MIT	A	50	Claude Code, Codex
ainb-fleet:daemonsstevengonsalvez/agents-in-a-box	Skill	27	13d ago	MIT	A	126	Claude Code
create-md-from-browsermcp-snapshotderailed-dash/dazbo-agent-skills	Skill	28	yesterday	MIT	B	77	Claude Code, Codex
ainb-fleet:atcstevengonsalvez/agents-in-a-box	Skill	27	13d ago	MIT	B	254	Claude Code
ainb-fleet:fleet-needsstevengonsalvez/agents-in-a-box	Skill	27	13d ago	MIT	B	112	Claude Code