symphony-rust: Skill for Claude Code

.agents/skills/symphony-land/SKILL.md

symphony-land is a skill for Claude Code, Codex from anantjain-xyz/symphony-rust. It costs 40 tokens per session (1,132 once invoked), scanned A, original, MIT.

A release skill for merging an approved, passing GitHub pull request into the main code branch. A pull request is a proposed set of code changes for review.

In plain words
What is it for?
Use it when an issue is in Symphony’s Merging state and its pull request is ready to land. It also records an already completed merge and moves the issue to Done.
Why use it?
It checks that the change is approved, synchronized with the latest main branch, conflict-free, and backed by passing automated checks before merging.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents).

This is anantjain-xyz/symphony-rust's own configuration. It tells Claude Code and Codex how to work on symphony-rust itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything symphony-rust configures →

Reuse

Borrowing it

Nothing to install: this file belongs to anantjain-xyz/symphony-rust. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/anantjain-xyz/symphony-rust/main/.agents/skills/symphony-land/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/anantjain-xyz/symphony-rust

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for symphony-land

README.md
[![agentmods](https://agentmods.dev/badge/skills/anantjain-xyz/symphony-rust/symphony-land/github.svg)](https://agentmods.dev/skills/anantjain-xyz/symphony-rust/symphony-land)
Your own site
<a href="https://agentmods.dev/skills/anantjain-xyz/symphony-rust/symphony-land"><img src="https://agentmods.dev/badge/skills/anantjain-xyz/symphony-rust/symphony-land/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.

agentmods 80×15 button for symphony-land

Your own site · 80×15
<a href="https://agentmods.dev/skills/anantjain-xyz/symphony-rust/symphony-land"><img src="https://agentmods.dev/badge/skills/anantjain-xyz/symphony-rust/symphony-land.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 40 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,132 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00040 $0.01132
Opus 5 $0.00020 $0.00566
Sonnet 5 $0.00008 $0.00226
Haiku 4.5 $0.00004 $0.00113

Measured 11d ago against content hash 2188805b4fff, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

symphony-land 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 11d 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

.agents/skills/symphony-land/SKILL.md · 79 lines

How it starts

The opening of the file, as written. The whole thing — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Land

Preconditions

  • Issue state is Merging.
  • gh auth status succeeds, and plain git push has credentials for the repo host. If relying on GitHub CLI for HTTPS git credentials, run gh auth setup-git first (gh auth setup-git --hostname <host> for a non-default host). GITHUB_TOKEN/GH_TOKEN alone can authenticate gh pr ... commands but is not enough for the symphony-push step's git push -u origin HEAD.
  • A PR is attached to the issue and is OPEN (not CLOSED/MERGED).

If the PR is already MERGED when entering this skill, skip the merge: record the merge SHA in the workpad and move the issue to Done.

Steps

  1. Inspect the PR:
    gh pr view --json number,state,mergeable,mergeStateStatus,reviewDecision,statusCheckRollup
    
    Required: state=OPEN, reviewDecision=APPROVED (or no required reviewers).
  2. Sync first — run the symphony-pull skill to merge origin/main. Conflicts must be resolved in code; never leave a DIRTY/CONFLICTING PR. Re-run validation after the merge.
  3. Push the merge result with the symphony-push skill.
  4. Wait for CI to be green. Don't rely on gh pr merge --auto — it only blocks on checks that branch protection marks as required, and many repos either configure no required checks or only a subset. Poll gh pr checks explicitly so the gate works the same whether the repo enforces checks at the GitHub level or not — every 30s, up to 30 minutes, before merging:
    for _ in $(seq 1 60); do
      gh pr checks
      rc=$?
      case "$rc" in
        0) break ;;       # all checks passed
        8) sleep 30 ;;    # checks still pending — keep waiting
        *) echo "PR checks failed (exit $rc)" >&2; exit 1 ;;
      esac
    done
    [ "$rc" -eq 0 ] || { echo "Timed out waiting for checks" >&2; exit 1; }
    
    gh pr checks exits 0 only when every check passed; 8 while any are pending; non-zero/non-8 if any failed. A failure or timeout falls into the failure-mode handler below: record the cause and move the issue to Rework.
  5. Squash-merge:
    gh pr merge --squash
    
    gh pr merge returning success does not guarantee the PR is merged — if the repo has a merge queue (or any auto-merge path kicks in), the command can return after enqueueing and the PR will still be OPEN while the queue runs. Verify in step 6 before continuing.
  6. Wait for the PR to reach terminal MERGED state — every 15s, up to 30 minutes:
    for _ in $(seq 1 120); do
      state=$(gh pr view --json state -q .state)
      case "$state" in
        MERGED) break ;;
        OPEN)   sleep 15 ;;
        *)      echo "PR ended in unexpected state: $state" >&2; exit 1 ;;
      esac
    done
    [ "$state" = "MERGED" ] || { echo "Timed out waiting for MERGED" >&2; exit 1; }
    
    A CLOSED (without MERGED) state or a timeout falls into the failure-mode handler below.
  7. Capture the merge commit (only after state=MERGED):
    gh pr view --json mergeCommit -q .mergeCommit.oid
    
  8. The remote head branch usually auto-deletes. If not, leave it — don't delete in scripts.
  9. Record the merge SHA in the workpad's ### Notes and move the issue to Done.

Read the full file on GitHub · 79 lines

Changes

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.

  1. 11d ago First seen · 79 lines · 40 tokens per session scan A 2188805b4fff

Subscribe to this mod's changes

symphony-land is a skill published in the GitHub repository anantjain-xyz/symphony-rust (11 stars, last pushed 28d ago), licensed MIT. It adds 40 tokens to every session and 1,132 once invoked, about $0.0002 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.