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 Shailesh200/prism --skill prism-safe-changegit clone --depth 1 https://github.com/Shailesh200/prismWrote 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/shailesh200/prism/prism-safe-change)<a href="https://agentmods.dev/skills/shailesh200/prism/prism-safe-change"><img src="https://agentmods.dev/badge/skills/shailesh200/prism/prism-safe-change/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/shailesh200/prism/prism-safe-change"><img src="https://agentmods.dev/badge/skills/shailesh200/prism/prism-safe-change.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 | $0.00066 | $0.00593 |
| Opus 5 | $0.00033 | $0.00296 |
| Sonnet 5 | $0.00013 | $0.00119 |
| Haiku 4.5 | $0.00007 | $0.00059 |
Grade A, and why
prism-safe-change 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 4d 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 — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Look before you edit
The failure this prevents is specific: an agent reads two or three open files, concludes a symbol is used in one place, changes it, and breaks four call sites it never opened. Grep does not reliably find them — re-exports, aliased imports, and dynamic references all hide from a text search. A resolved dependency graph does find them.
Before editing unfamiliar code
Call blast_radius on the file or symbol first. It returns what depends on the
target and how far the effect reaches.
Read the result before deciding scope. A small radius means edit freely. A large one means the change needs care, and possibly a smaller first step. Say which you found — the user cannot see the tool output, and "this is used in 31 places across 4 packages" changes how they want to proceed.
Skip this for code you have already read in full this session, and for genuinely local edits: a comment, a string literal, a function body with no signature change. The habit is worth having, not worth performing.
Before renaming
rename_impact on the symbol. It returns every site that has to change
together. Rename all of them in one edit — a half-applied rename that
typechecks is worse than one that does not, because it means two names now
refer to the same thing.
Before deleting
safe_delete on the file or symbol. It reports whether anything still depends
on the target. If something does, either the deletion is wrong or the dependents
go first; say which and let the user choose.
When you need the shape of the code first
find_symbol/search_symbols— where is this definedfind_references— who calls itdependency_route— how does A reach B, when the coupling is not obviousexplain_area— what is this directory for
After the edit
test_impact on the paths you changed names the suites that cover them. Run
those rather than the whole suite when the full run is slow.
A note on job workers
If you are a Prism job worker, your intelligence tools answer against the host checkout, not your worktree. Structural facts — who imports this, what depends on it — are the same either way and are exactly what to ask for. Questions about code you just wrote are not; read your own files for those.
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.
- 4d ago First seen · 59 lines · 66 tokens per session scan A cf71553d62ec
prism-safe-change is a skill published in the GitHub repository Shailesh200/prism (3 stars, last pushed today), licensed MIT. It adds 66 tokens to every session and 593 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 2026-09-05.
Other skills, from other repositories
adversarial-reviewer
Adversarial code review that assumes bugs exist and hunts for them. Use when asked to review code, find bugs, audit for correctness, stress-test a PR, or when someone says "tear this apart" or "what's wrong with this". Give no benefit of the doubt — every line is guilty until proven innocent.
gsd-ns-review
Route to the appropriate quality / review skill based on the user's intent. gsd-code-review-fix was absorbed by gsd-code-review --fix in #2790.
issue
Use when starting a chain from a GitHub issue — turning an issue URL or number into a triaged, planned, dispatched, and reviewed pull request. Classifies the thread (bug → root-cause discipline, feature → plan chain, question → drafted reply), synthesizes a spec from the issue's own acceptance criteria, then runs the…
gitnexus
A code-graph analysis add-on for examining an existing codebase, including symbols, call paths, execution flows, and effects across repositories. It can query GitNexus through its command-line or MCP interfaces.
cleanup-code-inspections
Reduce technical debt and improve code quality by systematically resolving static analysis warnings.
superlint
This skill describes the mandatory standard operating procedure for using our internal SuperLint tool. Use this when tasks require fixing code quality issues according to corporate standards.