Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add Jakeintech/waybill/plugin install waybillWrote 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/jakeintech/waybill/salvage)<a href="https://agentmods.dev/skills/jakeintech/waybill/salvage"><img src="https://agentmods.dev/badge/skills/jakeintech/waybill/salvage.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 | $0.00139 | $0.01135 |
| Opus 5 | $0.00069 | $0.00567 |
| Sonnet 5 | $0.00028 | $0.00227 |
| Haiku 4.5 | $0.00014 | $0.00113 |
Grade A, and why
salvage scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 6d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Salvage
Work that shipped without a ticket still burned real tokens and produced real receipts. Salvage recovers it: the engine groups the unmanifested spend, you propose names for what each group plainly was, the user confirms one group at a time, and the ledger gains reconstructed — honestly labeled — entries.
"${CLAUDE_PLUGIN_ROOT}/bin/waybill" mine --all # catch-up metering first, always
"${CLAUDE_PLUGIN_ROOT}/bin/waybill" query untracked [--from <iso>] [--to <iso>]
.data.clusters is the worklist: each cluster carries its kind
(story_key — a key seen in branches but never logged or synced;
branch — unattributed sessions grouped by branch; adhoc;
unattributed), its receipts (sessions, branches, repo, time window,
keys seen), and its tokens. .data.untracked_pct is the headline.
Correlate with real artifacts (optional, recommended)
For clusters with a repo, fetch the merged changes for the cluster's time window so titles and artifacts come from real receipts:
"${CLAUDE_PLUGIN_ROOT}/bin/waybill" sync-plan --local-repo <path> --since <cluster.first_ts> \
> /tmp/waybill-salvage-changes.json
Match changes to clusters by branch name or key. A matched change gives the cluster a real title (the commit/PR subject) and a real artifact.
Propose, then apply — one tap per cluster
For each cluster, in token order, present one line — proposed title,
kind, tokens, sessions, date range, the receipt it came from — and ask
one question: log it (as story:<KEY> when a key exists, else as an
adhoc label or a keyless entry), or leave it. Titles come from the
receipts only: branch names, commit subjects, keys. Never invent a
tracker key, a title, or an estimate.
To apply a confirmed cluster:
- For
branch/unattributedclusters, pin each session to the chosen account so the spend re-attributes (skip forstory_key/adhoc— already attributed):
"${CLAUDE_PLUGIN_ROOT}/bin/waybill" append --stream ledger --commit --event '{
"ts": "<cluster.last_ts>", "kind": "pin",
"session_id": "<session_id>", "account": "<story:KEY | adhoc:label>",
"tracker_key": <"KEY" | null>, "range": null,
"notes": "salvage: reconstructed from receipts"
}'
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.
- 6d ago First seen · 102 lines · 139 tokens per session scan A 79f7769db6f9
salvage is a skill published in the GitHub repository Jakeintech/waybill (1 stars, last pushed 13d ago), licensed MIT. It adds 139 tokens to every session and 1,135 once invoked, about $0.0007 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
worktrees
Use when fanning several tickets into parallel branches and git worktrees, with related tickets grouped together.
situate-refocus
Use when a branch may have drifted from its ticket or pull-request goal and needs its work and gaps reclassified.
situate
Gain situational awareness — read the branch, its diff, its PR, its tickets, and the project's own conventions, and report where the work stands.
what
Use when the user asks what is going on and needs a five-line summary of the session, branch, pull request, and ticket.
collaborative-engineering-agent
Unified SDLC skill for Agentic Project Management, GitOps/SecOps, and Dialectical Review loops.
situate-situational-awareness
Use when you came back to a branch/PR: the work you were in the middle of, where it left off, repo state, and what reviewers ask or the PR waits on.