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 photostructure/coding-skills --skill findgit clone --depth 1 https://github.com/photostructure/coding-skillsWrote 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/photostructure/coding-skills/find)<a href="https://agentmods.dev/skills/photostructure/coding-skills/find"><img src="https://agentmods.dev/badge/skills/photostructure/coding-skills/find/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/photostructure/coding-skills/find"><img src="https://agentmods.dev/badge/skills/photostructure/coding-skills/find.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 | $0.00082 | $0.00818 |
| Opus 5.5 | $0.00033 | $0.00327 |
| Sonnet 5.5 | $0.00016 | $0.00164 |
| Haiku 4.5 | $0.00008 | $0.00082 |
Grade A, and why
find 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.
How it starts
The opening of the file, as written. The whole thing — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Find the Session Behind a Change
More on these workflows: photostructure.com/coding (no dedicated
findarticle yet)
Report which local agent session wrote a change that is still uncommitted, and give the user a command that resumes it.
Run the finder
Resolve the bundled scripts/find_session.py
relative to this skill directory. Run it with the host's Python 3 launcher from
inside the repository that holds the change:
python3 scripts/find_session.py <path-or-snippet>
- A path to a file with uncommitted changes attributes that file's whole diff against HEAD.
- Any other argument is a snippet of changed text. The finder locates it in the diff against HEAD, untracked files included, and attributes only the lines it spans. Indentation, line breaks, and leading comment markers are ignored, so a comment copied across wrapped lines still matches. Pass a multi-line snippet as one quoted argument.
--days Nsearches transcripts modified in the last N days (default 14).--limit Ncaps the candidates shown (default 5).
On Windows, py -3 is a common equivalent.
How it attributes a change
The finder reads the transcripts that both supported agent CLIs keep under the user's home directory; the script's docstring names the directories and the environment variables that relocate them. It keeps only writes that succeeded, and scores each session by how many of the target's changed lines its writes added or removed. It counts:
- patches recorded by the file-editing tools;
- patch envelopes applied through a code-execution tool;
- shell commands that write the file and either name its absolute path or run inside its checkout, as weaker evidence, reported as "only through shell commands";
- writes to a path that no longer exists but has the target's file name and lies inside the same checkout, outside git-ignored directories, because the file was moved after them.
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 11d ago First seen · 77 lines · 82 tokens per session scan A 0ece07e20780
find is a skill published in the GitHub repository photostructure/coding-skills (4 stars, last pushed 3d ago), licensed MIT. It adds 82 tokens to every session and 818 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-09-26.
Other skills, from other repositories
pr-review
Address feedback left on a GitHub pull request: fetch unresolved review threads, make agreed Elixir/Phoenix code fixes, reply, and resolve. Use for a PR URL/number or reviewer comments. NOT for pre-PR review, findings triage, or CI monitoring.
phx-pr-review
Address feedback left on a GitHub pull request: fetch unresolved review threads, make agreed Elixir/Phoenix code fixes, reply, and resolve. Use for a PR URL/number or reviewer comments. NOT for pre-PR review, findings triage, or CI monitoring.
signing-preflight
Before the first commit of a session, check that commit signing will work — the key is loaded and unlocked — and ask the operator to unlock it once, up front, instead of discovering it after a hundred unsigned commits. Never disables signing silently, never re-signs history without asking. Use at the start of…
github-pr-creation
Creates GitHub Pull Requests with automated validation and task tracking. Use when user wants to create PR, open pull request, submit for review, or check if ready for PR. Analyzes commits, validates task completion, generates Conventional Commits title and description, suggests labels. NOTE - for merging existing…
git-commit
Creates git commits following Conventional Commits format with type/scope/subject. Use when user wants to commit changes, create commit, save work, or stage and commit. Enforces project-specific conventions from CLAUDE.md.
phx-watch-pr
Watch an Elixir/Phoenix PR with an Amp Orb keep-alive lease until required non-deployment CI is green and review threads are resolved.