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/qwerfunch/cladding/checkpointnpx skills add qwerfunch/cladding --skill checkpointgit clone --depth 1 https://github.com/qwerfunch/claddingWhat 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 | $0.00090 | $0.00514 |
| Opus 5 | $0.00045 | $0.00257 |
| Sonnet 5 | $0.00018 | $0.00103 |
| Haiku 4.5 | $0.00009 | $0.00051 |
Grade A, and why
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 yesterday.
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.
What it actually says
Cladding checkpoint
Run clad checkpoint <featureId> from the project root. Iron Law backbone Phase 1 (iron-law.md §2.5) — the verb only stamps the audit-log entry; it never mutates the working tree or invokes git commit. The maintainer keeps the option to freeze the state with a normal git commit on top.
The checkpoint event payload carries:
featureId— the spec id, accepts bothF-NNNlegacy andF-<hash6>(v0.3.9+) shapes.gitHead— full 40-char commit sha at the time of the call (ornullwhen the project is not a git repository).specDigest— sha-256 over the merged spec for replay verification.timestamp— ISO 8601.
clad checkpoint F-001
clad checkpoint F-a3f9c2
The output is a single Pulse line: ✓ checkpoint · <featureId> head=<sha12> digest=<digest12>. The event lands in .cladding/events.log.jsonl as type: "feature_checkpoint" and can be inspected with clad doctor --json or clad_get_events over MCP.
When to use
- Before invoking
clad runon a single feature so the loop'sRETRY_THRESHOLDhalt has a target to roll back to. - Before a manual refactor large enough that
git stashis unwieldy. - Right after
clad syncreports the spec is valid, so the checkpoint pins exactly the validated spec digest the implementation will start from.
Pair with
clad rollback <featureId> — prints the maintainer-runnable git checkout <sha> for the latest checkpoint and stamps a feature_rolled_back event. The pair forms the v0.3.X Iron Law backbone for safe autonomous progress; see skills/rollback/SKILL.md.
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.
- yesterday First seen · 32 lines · 90 tokens per session scan A f723e8cfb828
checkpoint is a skill published in the GitHub repository qwerfunch/cladding (14 stars, last pushed 3d ago), licensed MIT. It adds 90 tokens to every session and 514 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 2026-08-30.
Other skills, from other repositories
map-plan
ARCHITECT phase - decompose complex tasks into atomic subtasks with research, spec, and branch-scoped plan artifacts under .map.
map-review
Interactive 4-section code review using monitor, predictor, and evaluator agents plus the user and maintainer role reviewers on current changes. Use when reviewing a diff, PR, or staged work before merge. Do NOT use to plan or implement; use map-plan or map-efficient.
map-debug
Structured MAP debugging via task-decomposer, actor, and monitor agents. Use when reproducing a bug, isolating a regression, or diagnosing an error with specialized agents — including failing or flaky tests (pytest AssertionError), crashes and segmentation faults, memory-corruption or memory errors in native/C…
map-learn
Capture reusable lessons after a completed MAP workflow. Use when a MAP run has finished and you want rules written to .claude/rules/learned/ from a workflow summary or handoff. Do NOT use during active implementation.
map-efficient
State-machine MAP execution workflow for Codex. Use when implementing an approved MAP plan end to end, resuming from branch MAP taskplan or stepstate.json artifacts, or running non-trivial multi-subtask work. Use map-fast for tiny one-shot edits.
map-task
Execute a single subtask from an existing MAP plan via Actor and Monitor. Use when map-plan has decomposed work and you want fine-grained control over one subtask. Do NOT use without an existing plan; run map-plan first.