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 skills/phuonghx/aim-cli/batch-operationsnpx skills add phuonghx/aim-cli --skill batch-operationsgit clone --depth 1 https://github.com/phuonghx/aim-cliWhat 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 | $0.00068 | $0.00909 |
| Opus 5 | $0.00034 | $0.00454 |
| Sonnet 5 | $0.00014 | $0.00182 |
| Haiku 4.5 | $0.00007 | $0.00091 |
Grade A, and why
batch-operations 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 yesterday.
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 — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Sweeping Changes Across Many Files
When the same edit needs to land in dozens of places, treat it as a controlled operation: scope it, preview it, run it, then prove nothing broke.
Is This the Right Tool?
Fits well:
- Renaming a symbol everywhere it appears
- Dropping a shared import into a whole folder
- Synchronizing a version string across manifest files
- Stamping the same boilerplate onto a set of similar modules
- Swapping a deprecated call for its replacement repo-wide
Poor fit:
- A change confined to one file (edit it directly)
- Edits that differ from file to file (do them one by one)
- Anything needing case-by-case reasoning per file (delegate per area)
The Four-Step Loop
Step 1 — Pin Down the Change
Write the operation explicitly before touching anything:
Match: [the exact token or pattern]
Becomes: [the exact replacement]
Within: [glob of files in scope, e.g. "lib/**/*.js"]
Skip: [files to leave alone, e.g. "**/*.spec.js"]
Step 2 — Look Before You Leap
Always enumerate the impact first. Never start replacing blind.
# Which files contain it?
grep -rl 'oldName' lib --include='*.js'
# How many hits per file (drop the zero-hit files)?
grep -rc 'oldName' lib --include='*.js' | grep -v ':0$'
# See the actual lines, with line numbers
grep -rn 'oldName' lib --include='*.js'
Hard rule: surface the list of affected files to the user before you modify a single one.
Step 3 — Run the Sweep
Plain text substitution:
# Linux / macOS
find lib -name '*.js' -exec sed -i 's/oldName/newName/g' {} +
# Windows (PowerShell)
Get-ChildItem -Path lib -Recurse -Filter *.js |
ForEach-Object { (Get-Content $_) -replace 'oldName','newName' | Set-Content $_ }
Anything beyond a flat find/replace — inserting imports, wrapping blocks, reordering — should go through the Edit tool per file, processed in a stable order (alphabetical, or following the dependency chain) so the run is reproducible.
Step 4 — Confirm It Held
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.
- yesterday First seen · 106 lines · 68 tokens per session scan A be046d1d97f4
batch-operations is a skill published in the GitHub repository phuonghx/aim-cli (1 stars, last pushed 2mo ago), licensed MIT. It adds 68 tokens to every session and 909 once invoked, about $0.0003 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
hs-release
Cut a core Hindsight release (vX.Y.Z) and open the changelog + blog PR. Use when asked to cut/start a release, bump the version, or publish a new Hindsight version.
hindsight-local
Store user preferences, learnings from tasks, and procedure outcomes. Use to remember what works and recall context before new tasks. (user).
research-repository
Build a repository that makes findings findable, reusable, and cumulative across teams. Use when the same research keeps getting redone. For synthesising one study, use affinity-diagram.
design-negotiation
Advocate for design quality, scope, and timeline with partners and leadership using evidence and shared goals. Use in the conversation itself. For the commercial vocabulary behind it, use business-design (ux-strategy).
user-persona
Build research-grounded personas with goals, frustrations, and behavioural patterns. Use when decisions need a consistent user reference. For one session's emotional snapshot use empathy-map; for motivation framing use jobs-to-be-done.
version-control-strategy
Define version control for design files, components, and libraries — branching, naming, and release. Use when file history is chaotic. For design system contribution rules, use design-system-governance (design-systems).