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 skills add tmj-90/gaffer --skill resolve-merge-conflictgit clone --depth 1 https://github.com/tmj-90/gafferWrote 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/tmj-90/gaffer/resolve-merge-conflict)<a href="https://agentmods.dev/skills/tmj-90/gaffer/resolve-merge-conflict"><img src="https://agentmods.dev/badge/skills/tmj-90/gaffer/resolve-merge-conflict/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/tmj-90/gaffer/resolve-merge-conflict"><img src="https://agentmods.dev/badge/skills/tmj-90/gaffer/resolve-merge-conflict.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 | $0.00107 | $0.01206 |
| Opus 5 | $0.00053 | $0.00603 |
| Sonnet 5 | $0.00021 | $0.00241 |
| Haiku 4.5 | $0.00011 | $0.00121 |
Grade A, and why
resolve-merge-conflict 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 10d 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 — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Resolve a merge conflict (preserve both intents, branch-only)
An approved ticket's delivery branch (gaffer/...) conflicts with the default branch:
work landed on the default branch after this branch forked, and the two edits collide.
The factory will NOT force-merge over a conflict. Your job is to reconcile the two
sides honestly on the branch so a human can re-review the resolved diff and re-approve
it — after which a later merge lands cleanly.
You are resolving, not re-implementing. Preserve what BOTH sides intended. The conflict exists because two real changes overlapped; the answer is almost never "keep mine and drop theirs" (or the reverse) — it's an edit that satisfies both.
Steps
- Understand both sides first. Before touching anything, read what each side
changed and why:
- This branch:
git log <defaultBranch>..HEADandgit diff <defaultBranch>...HEAD— the work this ticket delivered. - The default branch:
git log HEAD..<defaultBranch>— what landed since the fork. You cannot resolve a conflict you don't understand. If a side's intent is unclear, read the surrounding code and the ticket's acceptance criteria.
- This branch:
- Merge the default branch INTO the branch. Run
git merge <defaultBranch>while on the delivery branch. This brings the default branch's changes onto the branch and surfaces the conflicts as conflict markers — the safe direction, because it leaves the default branch untouched. - Resolve every conflict by preserving both intents. For each conflicted hunk,
produce an edit that keeps the behaviour BOTH sides were going for. Never blindly
--ours/--theirsa whole file to make markers disappear — that silently discards one side's work. If two changes are genuinely irreconcilable, choose the one the ticket's acceptance criteria require and note explicitly what you set aside and why. - Run the repo's tests. A resolution that compiles but breaks tests is not resolved.
Use the
run-testsskill (or the repo's test command). If the merge surfaced a real behavioural clash, the failing test is telling you the two intents actually conflict — fix the reconciliation, don't delete the test. - Commit the resolution ON THE BRANCH. Complete the merge with a normal merge
commit on the delivery branch (
git commitafter staging the resolved files). The branch now contains both intents plus the reconciliation. - Record a short resolution summary. Write 3–6 lines: which files/hunks conflicted, how you preserved each side, anything you had to set aside, and the test result. Record it as the ticket's resolution evidence via the Dispatch MCP, and print it as the last line of your message. This summary is what the human re-reviews.
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.
- 10d ago First seen · 78 lines · 107 tokens per session scan A fb8675dda4d0
resolve-merge-conflict is a skill published in the GitHub repository tmj-90/gaffer (2 stars, last pushed 3d ago), licensed Apache-2.0. It adds 107 tokens to every session and 1,206 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 2026-08-31.
Other skills, from other repositories
code-review-loop
Iterative review+fix loop for BASESHA..HEAD: generate findings, apply accepted fixes, run checks, commit, and re-review up to 3 iterations or until clean.
dedup
Dedupe-only pass for BASESHA..HEAD: remove duplicate code introduced by the diff or reuse existing shared utils; applies changes + commits.
plan-critique-loop
Critique and revise an existing plan doc up to 3 iterations, using accept/reject triage and stopping early when no important feedback remains. Use when refining a plan/.md before implementation.
besimple-tiny-broccoli
Small-change wrapper: implement → run repo checks → atomic commit → run dedup (BASESHA..HEAD).
claude-simplify-wrapper
Run Claude's built-in /simplify skill on BASESHA..HEAD, validate checks, and commit.
aiwg-pr
AIWG-specific pull request delivery workflow for AIWG product/workspace changes; not the generic repository PR process.