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 fledgeling-co/fledgeling-plugins/plugin install shipyardWrote 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/fledgeling-co/fledgeling-plugins/gap-fix)<a href="https://agentmods.dev/skills/fledgeling-co/fledgeling-plugins/gap-fix"><img src="https://agentmods.dev/badge/skills/fledgeling-co/fledgeling-plugins/gap-fix/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/skills/fledgeling-co/fledgeling-plugins/gap-fix"><img src="https://agentmods.dev/badge/skills/fledgeling-co/fledgeling-plugins/gap-fix.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 | $0.00170 | $0.01606 |
| Opus 5.5 | $0.00068 | $0.00642 |
| Sonnet 5.5 | $0.00034 | $0.00321 |
| Haiku 4.5 | $0.00017 | $0.00161 |
Grade A, and why
gap-fix 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 1mo 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 — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Pipeline Gap-Fix — remediation, and the road back from Needs More Work
Finish the job the worker started: close whatever the delivered implementation still misses
versus the original requirements, in code, on the same branch — then hand the item back to
shipyard:verify rather than grading it yourself. This is the failure path existing on purpose: a
Needs More Work verdict is a work order, not a dead end.
Shared canon by pointer: ${CLAUDE_PLUGIN_ROOT}/references/ → tracker-adapter.md,
model-lanes.md, executor-lanes.md, evidence-rules.md, operational-rules.md, and the
worker's ../work/references/miss-classes.md.
Running as a Gemini model? Read gemini.md in this directory first, then follow this file with the overrides it names. It scopes prior-model routing evidence to the models measured, turns this skill's ten prose prohibitions into a bound ledger read back off the diff, splits Phase A's six dimensions into six passes each writing a file the fix phase must open, and makes every number in the Phase C record carry the command that produced it. Other models skip it.
Inputs
- An id at
Needs More Work(the verifier's verdict table is the primary gap list) orDeveloper Review/In Reviewwith provided gaps (inline, a file, a## Gapssection, a QA list). Provided gaps merge into the self-audit; they never replace it — a QA list is a floor, not a ceiling. - Optional
--dry-run: audit and report the gaps + intended fixes; change no code.
Setup
- Find the branch: reuse
.worktrees/<ID>; elsegit worktree add .worktrees/<ID> ai/<id>; else there is nothing to fix — say so and recommendshipyard:work(NEEDS WORK). Check the base staleness (merge-base --is-ancestor) before trusting a reused worktree. - Read the spec/ticket + full thread, the plan, and the verifier's verdict from the main tree
at absolute paths. Human answers are authoritative; the verdict's
Missed/Partialrows and their evidence are confirmed findings arriving pre-verified. - Post the round marker before working (crash-safe counter,
tracker-adapter.md): count prior gap-fix rounds from the thread; three rounds without reachingDoneparks the item with a blocker note naming what keeps failing — a converging loop shrinks its gap list every round, and one that doesn't is diagnosing the wrong layer. - All code edits inside
WT; disjoint scopes; docs stay in the main tree.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 1mo ago Changed · -5 lines · +2 tokens per session 41621002d2fc
- 1mo ago First seen · 102 lines · 168 tokens per session scan A c2f7a83326e3
gap-fix is a skill published in the GitHub repository fledgeling-co/fledgeling-plugins (2 stars, last pushed 4d ago), licensed MIT. It adds 170 tokens to every session and 1,606 once invoked, about $0.0007 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 2026-09-04.
Other skills, from other repositories
bug-triage
Re-evaluate open bugs — priority vs severity, assign to sprints, surface systemic trends. Run when the count grows.
systemic-issue-triage
Trigger: new issue, bug report, triage, backlog, issue flood, community report, root cause, dead-end, blocked user. Attack issues by root class, never one-by-one; fixes must shrink the system, not grow it.
triage-issue-reports
Triage Slack issue reports with one thread-only verdict, evidence review, cause-aware routing, tracker dedupe, and fail-closed ticket creation. Use only from the configured Benny triage automation.
triage-issue
Intelligently triage bug reports and error messages by searching for duplicates in Jira and offering to create new issues or add comments to existing ones. When an agent needs to: (1) Triage a bug report or error message, (2) Check if an issue is a duplicate, (3) Find similar past issues, (4) Create a new bug ticket…
moai-lane-watchdog
One lane stall watchdog iteration: measure lane progress on three channels, classify the stall cause, apply the remedy or resolve the judgment through the decision ladder — instead of waiting on a reply — then record the outcome and report. Reads the unified --auto doctrine at…
investigation
Create an investigation ticket + live-doc for sustained root-cause work (retros, bug archaeology, regression hunts).