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/tessaryai/plugins/implement-issuenpx skills add tessaryai/plugins --skill implement-issuegit clone --depth 1 https://github.com/tessaryai/pluginsWhat 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 | $0.00071 | $0.01778 |
| Opus 5 | $0.00036 | $0.00889 |
| Sonnet 5 | $0.00014 | $0.00356 |
| Haiku 4.5 | $0.00007 | $0.00178 |
Grade A, and why
implement-issue scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 153 lines — stays where its author put it; the contents beside it link to each section on GitHub.
implement-issue
Internal crew primitive — dispatched by
/crew:run. You are running because the orchestrator selected this as one step of a larger workflow; carry out the work below. This skill is not meant to be invoked on its own — user requests go to/crew:run, which decides when implementation is preceded by triage and followed by review and fixes.
You are the team lead for autonomous implementation. You convene a deliberative team of advisory specialists, synthesize their perspectives, and are the only one who writes code and opens the PR. Your autonomy ceiling is a review-ready PR — you never merge.
The argument is the work to implement: a GitHub issue number (e.g.
/crew:implement-issue 42) or a freeform task / ledger slug (local). If missing, ask.
0. Load config, guardrails, and mode
python3 "${CLAUDE_PLUGIN_ROOT}/lib/load_config.py"
Read and obey: guardrails.protected_paths,
labels.{bug,task,agent_pr,needs_human}, team.personas, commands.{install,lint,typecheck,test},
ledger.dir, local.isolation, and review_standards.source. Also read the project's
AGENTS.md/CLAUDE.md for coding conventions — your change must follow them.
Then read ${CLAUDE_PLUGIN_ROOT}/reference/work-model.md and resolve the mode before any
gh call. It governs where you read context, where you write code (the worktree), and how
you persist the result (work-model.md §2 and §4).
1. Read the work item
- GitHub mode:
gh issue view <N> --comments. Detect whether it carrieslabels.bugorlabels.task. - Local mode: read
<ledger.dir>/<slug>/task.mdandtriage.md. Thekindfield (bug/task) is intask.md's frontmatter. If there is notriage.mdyet, triage first (see Constraints).
The kind picks your commit/PR prefix later (fix: vs feat:). Read the triage analysis and
gather context by reading the affected files it names.
If the work is far bigger than one PR. If, reading the triage, you find the change would
span many modules or need a broad rewrite — far more than one review-ready PR — do not
attempt it as a single implementation. Stop and report a decomposition plan (numbered
independent units: description, target, primitive, depends_on) flagged
scale-out-recommended back to the orchestrator, which decides whether to fan it out and
always confirms with the user first (${CLAUDE_PLUGIN_ROOT}/reference/scale-out.md).
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.
- 2d ago First seen · 153 lines · 71 tokens per session scan A 174b5e82ffe9
implement-issue is a skill published in the GitHub repository tessaryai/plugins (3 stars, last pushed 14d ago), licensed MIT. It adds 71 tokens to every session and 1,778 once invoked, about $0.0004 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
ghost-decode
Use when a video hides text in moving dots or noise — "ghost font" clips, motion-defined text, random-dot kinematograms, TV-static videos with a secret message, text readable only while playing but invisible in any paused frame, or the user asks what a ghost-font video says.
watch
File sentinel that monitors the working directory for changes and marker comments, then auto-triggers appropriate skills. Poll-based via git diff against the last scan commit. Writes intake items for batch processing and routes marker actions through /do. Use for automatic reactions to file changes; do NOT use for…
review
5-pass structured code review — correctness, security, performance, readability, consistency.
live-preview
Mid-build visual verification loop. Takes screenshots of components during construction, not just after. Catches visual regressions and invisible features before they compound. Requires Playwright or similar screenshot tool.
wiki
Markdown-first knowledge base where the LLM acts as librarian. Ingests raw sources, compiles and interlinks topic files, self-maintains an index. No vector DB or embeddings required -- uses LLM-native navigation over structured markdown up to 400K words.
marshal
Meta-orchestrator that takes any direction — broad, specific, or vague — and autonomously chains skills and context into actionable work. Gathers context from codebase, docs, and memory. Only asks the user when it genuinely cannot proceed. Single-session orchestrator.