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/pronskiy/php-src-developer/bug-contextnpx skills add pronskiy/php-src-developer --skill bug-contextgit clone --depth 1 https://github.com/pronskiy/php-src-developerWhat 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 | $0.00153 | $0.02417 |
| Opus 5 | $0.00077 | $0.01208 |
| Sonnet 5 | $0.00031 | $0.00483 |
| Haiku 4.5 | $0.00015 | $0.00242 |
Grade A, and why
bug-context 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 — 197 lines — stays where its author put it; the contents beside it link to each section on GitHub.
bug-context
Entry point of the php-src bug-fix flow. Pulls the GitHub issue, synthesises it, and writes the Context phase of SPEC.md.
Inputs
- Issue identifier (required) — a GitHub issue number (
12345),GH-12345, or full URL (https://github.com/php/php-src/issues/12345). PHP_SRC_DIR(required) — resolved per_shared/php-src-detection.md(auto-detect cwd inside checkout, or honour the env var override). Refuse if neither path resolves.ghCLI (required) — must be authenticated (gh auth status). If unauthenticated, stop and tell the user.
What it produces
SPEC.md in the task directory (resolved per _shared/task-dir.md; default $PHP_SRC_DIR/.claude/php-core-dev/gh-<N>/SPEC.md) with:
- Frontmatter:
type: bug,linked:set to the GH issue URL,php_src_ref:set to the currentgit rev-parse HEADof$PHP_SRC_DIR,target_branch:resolved per_shared/branch-detection.md(see step 6 below),created:today's date,status: in-progress. ## Contextsection with a synthesised problem statement.- Phase skeletons (Reproduction, Analysis & Plan, Implementation, Verification) — all
status: todo, with their guardrails pre-declared. - Empty
## Open Questions. - A first Progress Log entry.
Workflow
1. Resolve PHP_SRC_DIR and validate environment
Resolve PHP_SRC_DIR using the algorithm in _shared/php-src-detection.md (env-var override or walk-up from $PWD). If neither path resolves, refuse with the detection doc's error message — do not guess.
gh auth status >/dev/null 2>&1 || { echo "gh CLI not authenticated. Run: gh auth login"; exit 1; }
2. Resolve issue identifier
Accept any of:
12345GH-12345https://github.com/php/php-src/issues/12345https://github.com/<owner>/<repo>/issues/12345(rare — non-php/php-srcforks)
Default repo is php/php-src when only a number is given.
3. Fetch issue data
gh issue view <N> --repo php/php-src --json number,title,body,labels,state,url,comments,createdAt,author
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 · 197 lines · 153 tokens per session scan A 93ca4548720c
bug-context is a skill published in the GitHub repository pronskiy/php-src-developer (8 stars, last pushed 3mo ago), licensed MIT. It adds 153 tokens to every session and 2,417 once invoked, about $0.0008 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…