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 AtlasOmnia/hermes-custom-pack --skill stale-patch-reconciliationgit clone --depth 1 https://github.com/AtlasOmnia/hermes-custom-packWrote 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/atlasomnia/hermes-custom-pack/stale-patch-reconciliation)<a href="https://agentmods.dev/skills/atlasomnia/hermes-custom-pack/stale-patch-reconciliation"><img src="https://agentmods.dev/badge/skills/atlasomnia/hermes-custom-pack/stale-patch-reconciliation/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/atlasomnia/hermes-custom-pack/stale-patch-reconciliation"><img src="https://agentmods.dev/badge/skills/atlasomnia/hermes-custom-pack/stale-patch-reconciliation.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 | $0.00026 | $0.02146 |
| Opus 5 | $0.00013 | $0.01073 |
| Sonnet 5 | $0.00005 | $0.00429 |
| Haiku 4.5 | $0.00003 | $0.00215 |
Grade A, and why
stale-patch-reconciliation scanned grade A with 1 finding 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 5d 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.
Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
- Running `./.venv/bin/python -m pytest` from a gateway session can trip the terminal tool's lifecycle guard — `ValueError: embedded null byte` in `cron/lifecycle_guard.py`, triggered whenever the command's FIRST EXECUTA This is a copy
100% identical to stale-patch-reconciliation — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Stale Patch Reconciliation
Use when a patch/diff must be compared with, repaired against, or refreshed for a moving checkout — "is this patch still needed", "does upstream already contain it", "what changed since it was written", "reconcile X.diff with HEAD", or "make apply-patches pass again".
This skill has two explicit modes:
- Analysis mode (default): read-only archaeology and a minimal repair plan. Do not edit, reset, stash, clean, update, or restart.
- Repair mode (only when authorized): implement the invariant in an isolated worktree, run focused gates, regenerate the patch from the current baseline and an explicit file allowlist, then apply it to the live checkout only after clean/reverse checks pass. Preserve unrelated dirty work exactly.
Deliverable shape: (1) behavioral invariant, (2) exact gaps/call sites, (3) upstream status, (4) drift cause, (5) minimal repair, (6) focused gate evidence, and (7) artifact/applicator verification. Coordinate writer ownership through shared-worktree-agent-orchestration.
Core sequence
-
Read the full patch first. Paginate the whole diff; note every file touched and the old-file line numbers of each hunk. The hunks are the map for later drift attribution.
-
Git history archaeology — does the feature exist anywhere?
git log --all --oneline -i --grep=<feature>— commits mentioning it by namegit log --all --oneline -S'<feature>'— commits adding/removing the string (catches renames/variants)git log origin/main -S'<feature>'— empty means NOT upstream (private branches don't count as upstream)git merge-base --is-ancestor <sha> HEAD && echo YES || echo NO— ancestry testgit branch -a --contains <sha>— which branches carry the commits
- Snapshot-branch trap. If
git merge-base HEAD <branch>returns EMPTY output, the branch is likely built on a parentless snapshot commit. Confirm withgit log --format='%h parents: %P' -1 <sha>— no parents = root/snapshot commit (e.g. "chore: snapshot upstream main for private feature review"). Such a branch shares NO ancestry with HEAD, so lineage tools mislead; treat the branch's cumulative diff as the feature and ignore ancestry.
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.
- 5d ago First seen · 69 lines · 26 tokens per session scan A 9e7144820c38
stale-patch-reconciliation is a skill published in the GitHub repository AtlasOmnia/hermes-custom-pack (56 stars, last pushed 24d ago), licensed MIT. It adds 26 tokens to every session and 2,146 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 1 finding (runs shell commands). It is 100% identical to stale-patch-reconciliation, differing in 0 lines, and is treated as a copy.
Other skills, from other repositories
github-auth-recovery
Recover from broken GitHub auth flows when git/gh operations fail. Use when gh is not logged in, HTTPS push/pull asks for credentials or errors like could not read Username, a repo remote is HTTPS but SSH may already work, or when GitHub operations fail and the agent needs a deterministic path to diagnose auth method…
history
In D&D, History recalls significant past events, legendary figures, and ancient knowledge. The real-world version is temporal investigation: git blame across the entire project, reading changelogs to understand why a decision was made, reconstructing the sequence of events that led to a production incident, or…
magpie-setup-upstream-fix
Turn a framework bug or quirk the agent hit while running a Magpie skill or tool into a fix PR against apache/magpie — one PR per issue. First confirms the problem is a framework defect (not a local misconfiguration or a stale snapshot), then searches apache/magpie for an existing issue or PR that already covers it…
coding-worktree-recovery
Use this skill when coding-agent work is interrupted, an agent exits without a clean commit, multiple controllers target the same checkout, or the checkout produces inconsistent file/Git behavior.
parallel-orchestrator
Manage parallel Claude Code workstreams using git worktrees. Use when: splitting large tasks across multiple workers, coordinating parallel development, monitoring worker progress, integrating completed work, analyzing work item documents (code reviews, issue lists). Triggers: parallel, orchestrator, worktrees…
parallel-worker
Execute focused implementation tasks in a parallel workflow. Use when: working on assigned files in a worktree, making checkpoint commits, signaling dependencies or blockers, completing orchestrator-assigned tasks. Triggers: worker, checkpoint, worktree, assigned scope, commit prefix, parallel task.