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 commands/developerz-ai/ai-task-master/merge-prgit clone --depth 1 https://github.com/developerz-ai/ai-task-masterWrote 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/developerz-ai/ai-task-master/merge-pr)<a href="https://agentmods.dev/commands/developerz-ai/ai-task-master/merge-pr"><img src="https://agentmods.dev/badge/commands/developerz-ai/ai-task-master/merge-pr.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 | $0.00000 | $0.00503 |
| Opus 5 | $0.00000 | $0.00251 |
| Sonnet 5 | $0.00000 | $0.00101 |
| Haiku 4.5 | $0.00000 | $0.00050 |
Grade A, and why
merge-pr 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 3d 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.
What it actually says
aitm merge-pr
Drive an open PR to merge, then advance to the next PR group.
In the default automerge-on flow this logic runs inline inside aitm start — you only invoke aitm merge-pr directly when --no-automerge was used, or to resume a paused run.
Signature
aitm merge-pr
[--pr N] # default: state.json.currentPr
[--no-resume] # default: continue to next PR group after merge
Preconditions
.ai-task-master/state.jsonexists withstatus: awaiting-pr(or--prprovided explicitly).ghCLI authenticated.OPENROUTER_API_KEYset.
Flow
CLIloads state viaStateStore.GitHubClientfetches PR status and CI checks. Polls with exponential backoff until checks are conclusive.- On CI failure:
OrchestratorinvokesWorkerwith failure logs to fix and push. GitHubClientfetches unresolved review comments via GraphQL.- On unresolved comments:
OrchestratorinvokesReviewerto address each, push fixes, request re-review, resolve threads. - Loop 2–5 until checks green AND no unresolved comments remain.
GitHubClientmerges (squash by default).StateStoremarks the group merged.- Unless
--no-resume: re-enterWorkLoopon the next PR group. Otherwise exit 0.
Defaults
| Behavior | Default | Override |
|---|---|---|
| Automerge after green | on | --no-automerge on aitm start |
| Merge strategy | squash | --merge-method merge|rebase |
| Resume to next group | on | --no-resume |
Failure modes
| Mode | Handling |
|---|---|
| Merge conflict | Worker rebases onto base, retries push. |
| CI flaky | Backoff with jitter, retry within session cap. |
| Persistent failure | Exit 1, state preserved for inspection / resume. |
See also
./start.md../task-groups.md../subagents.md../github-integration.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.
- 3d ago First seen · 54 lines · 0 tokens per session scan A a6edd84c65e6
merge-pr is a command published in the GitHub repository developerz-ai/ai-task-master (5 stars, last pushed 28d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 503 tokens. 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 commands, from other repositories
triage
Classify/label newly opened GitHub issues missing labels.
fix-issues
Diagnose, reproduce, then fix reproducible open GitHub issues in parallel: one clean worktree/issue; symlink build artifacts to avoid rebuilds.
release
Release all packages at specified version.
cleanup
Autonomous cleanup-loop iteration: discover ONE target → complete execution → verify → report. Runs stateless: derive from current tree; assume prior runs left it consistent.
rp-build-cli
Build with rp-cli context builder → chat → implement.
rp-investigate-cli
Deep codebase investigation and architecture research with rp-cli commands.