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.
git clone --depth 1 https://github.com/akougkas/wtf-pWrote 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/commands/akougkas/wtf-p/wtfp-checkpoint)<a href="https://agentmods.dev/commands/akougkas/wtf-p/wtfp-checkpoint"><img src="https://agentmods.dev/badge/commands/akougkas/wtf-p/wtfp-checkpoint/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/commands/akougkas/wtf-p/wtfp-checkpoint"><img src="https://agentmods.dev/badge/commands/akougkas/wtf-p/wtfp-checkpoint.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00018 | $0.00901 |
| Opus 5 | $0.00009 | $0.00451 |
| Sonnet 5 | $0.00004 | $0.00180 |
| Haiku 4.5 | $0.00002 | $0.00090 |
Grade A, and why
wtfp:checkpoint scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Manage checkpoints
@${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: the declared portable records and authored artifacts selected for the snapshot.
Produce: project://checkpoints/{checkpoint} (create), project://archives/checkpoints/{checkpoint} (create), project://archives/recovery/{artifact} (create on restore), project://manifest (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
- For save, select concrete contained resources, copy their exact bytes into an immutable checkpoint archive, hash every entry, then create a non-blocking
state-snapshotcheckpoint that records the archive URI, logical resource URIs, record revisions, and SHA-256 values. Link the archive from the manifest and read everything back before success. - For list or inspect, report snapshot scope and verify that the archive, resources, revisions, and hashes still resolve without mutation.
- For restore, compare the selected snapshot with current resources, create and verify a pre-restore recovery archive, preview the exact replacements, and require a separate authorization immediately before applying them. Restore only snapshot-declared resources atomically, schema-validate records, verify hashes, and mark the checkpoint restored. Never use a commit, tag, checkout, reset, or branch movement as checkpoint storage.
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.
- 9d ago First seen · 75 lines · 18 tokens per session scan A 5284e4600412
wtfp:checkpoint is a command published in the GitHub repository akougkas/wtf-p (19 stars, last pushed 10d ago), licensed MIT. It adds 18 tokens to every session and 901 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other commands, from other repositories
apex-git-commit
Stage everything except agent-output/, infra/, and .github/skills/sensei/ (unless on feat/skills-sensei), auto-generate a conventional commit, push, then prompt to open or update a PR. CLI-only (git + gh).
merge-conflict-analysis
You are analyzing merge conflicts for PR #${{ pr-number }}.
backlog-sync
Sync local backlog with external PM tools (Azure DevOps, Jira, GitHub Issues).
validate-pr-description
Use when validating a PR title and description for conventional commit format, issue linking keywords, and template compliance before submission.
run-plan
Execute implementation plan phases for a change.
commit
Analyze uncommitted changes, create a branch if needed, and commit with a well-structured message.